© 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. 3340
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     Intelligence
    -0.07
     intelligence
    -0.07
    intelligence
    -0.07
    bourg
    -0.07
    ledi
    -0.07
    ullan
    -0.07
    VICE
    -0.07
    ÃĹ↵↵
    -0.06
    tent
    -0.06
    HING
    -0.06
    POSITIVE LOGITS
     majority
    0.08
     control
    0.08
     controlling
    0.08
     ownership
    0.08
     minority
    0.08
     exerc
    0.07
    _control
    0.07
     voting
    0.07
     owning
    0.07
     shares
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.