© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 30-LLAMASCOPE-RES-32K
    11. 7852
    Prev
    Next
    INDEX
    Explanations

    specific data-related functions or operations in a technical context, particularly within programming or database queries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãģ¬
    -0.14
     PROGMEM
    -0.12
     اÙĦتش
    -0.12
    mmas
    -0.12
    Ø°ÙĬ
    -0.12
     Chop
    -0.12
    ditor
    -0.12
    каж
    -0.12
    اÙĨس
    -0.11
    à¥įरव
    -0.11
    POSITIVE LOGITS
     count
    1.38
     Count
    1.25
    count
    1.22
    -count
    1.20
     counts
    1.16
     COUNT
    1.11
     counting
    1.11
    Count
    1.11
     counted
    1.07
    .count
    1.06
    Activations Density 0.550%

    No Known Activations