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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 31764
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and concepts

    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
     Math
    -0.22
    (boolean
    -0.17
    =Math
    -0.16
    (Math
    -0.16
    Math
    -0.15
    ]=[
    -0.14
     parseFloat
    -0.14
    .Math
    -0.14
     `$
    -0.14
     ðĿ
    -0.14
    POSITIVE LOGITS
    *sizeof
    0.26
    (nullptr
    0.23
    ->
    0.23
    ULL
    0.23
     nullptr
    0.22
    LL
    0.22
    (NULL
    0.21
    ->_
    0.21
    (std
    0.20
    [sizeof
    0.20
    Activations Density 0.135%

    No Known Activations