© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 25-LLAMASCOPE-RES-32K
    6. 12719
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations, specifically streets, and related urban features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases describing physical locations and routes in urban or residential settings, particularly related to streets, directions, and spatial relationships.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    descriptions of urban street environments and adjacent infrastructure, including parking, sidewalks, curbs, and traffic/route details.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bunk
    -0.18
    _refl
    -0.15
    umper
    -0.15
     circumference
    -0.14
    apg
    -0.14
    orks
    -0.14
     Spiral
    -0.14
     mê
    -0.14
     Counties
    -0.14
     forests
    -0.13
    POSITIVE LOGITS
     street
    0.60
    street
    0.50
    Street
    0.45
     Street
    0.44
     streets
    0.44
     STREET
    0.43
    _street
    0.38
    è¡Ĺ
    0.36
     Streets
    0.35
    .street
    0.35
    Activations Density 0.188%

    No Known Activations