© 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. 17-LLAMASCOPE-RES-131K
    11. 61163
    Prev
    Next
    INDEX
    Explanations

    references to variables, their classifications, and structural organization in data or programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    asca
    -0.08
    -basket
    -0.07
    ipp
    -0.07
    udu
    -0.06
    .Dispatcher
    -0.06
     باÙĤ
    -0.06
    ente
    -0.06
    inson
    -0.06
    -svg
    -0.06
    (åľŁ
    -0.06
    POSITIVE LOGITS
     within
    0.33
     Within
    0.30
    within
    0.30
    Within
    0.29
    _within
    0.26
     dentro
    0.25
     inside
    0.22
     внÑĥÑĤÑĢи
    0.19
    inside
    0.19
     binnen
    0.18
    Activations Density 0.165%

    No Known Activations