© 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. 84605
    Prev
    Next
    INDEX
    Explanations

    numerical data or statistics, particularly in a structured format

    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
    ModelProperty
    -0.07
    ayet
    -0.07
    бом
    -0.07
    रत
    -0.07
    мени
    -0.07
    ptune
    -0.07
    hait
    -0.07
    é¾Ħ
    -0.07
    argent
    -0.07
    HEET
    -0.07
    POSITIVE LOGITS
     winds
    0.06
     late
    0.06
    LAG
    0.06
     Counsel
    0.06
     loud
    0.05
     wind
    0.05
     Undert
    0.05
    $sub
    0.05
     Kong
    0.05
    iba
    0.05
    Activations Density 0.001%

    No Known Activations