© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 31-LLAMASCOPE-RES-32K
    11. 2370
    Prev
    Next
    INDEX
    Explanations

    specific syntax elements and formatting in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .
    -0.80
    ,
    -0.77
    :
    -0.46
    .↵
    -0.45
    ;
    -0.45
    .↵↵
    -0.34
     and
    -0.32
    !
    -0.31
    ,↵
    -0.30
    ?
    -0.29
    POSITIVE LOGITS
     ÂŃ
    0.15
     “âĢ¦
    0.15
    íĬľ
    0.13
     kıs
    0.12
    ’B
    0.12
     ..."↵
    0.12
    .Css
    0.12
     hạt
    0.12
     içinde
    0.11
     ”↵
    0.11
    Activations Density 0.092%

    No Known Activations