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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 24-LLAMASCOPE-RES-32K
    6. 13585
    Prev
    Next
    INDEX
    Explanations

    inhabited locations or areas of interest, particularly in a context involving fields and spaces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vit
    -0.16
     Vit
    -0.16
    timeofday
    -0.15
    rgan
    -0.15
    abyrin
    -0.15
    amage
    -0.15
    vit
    -0.15
    ancode
    -0.15
    æı
    -0.14
    ê¶Į
    -0.14
    POSITIVE LOGITS
    trip
    0.26
     trip
    0.23
    work
    0.22
     field
    0.22
     trips
    0.21
    ing
    0.20
     Trip
    0.20
    arshal
    0.19
     sob
    0.19
    (field
    0.19
    Activations Density 0.012%

    No Known Activations