© 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. 60877
    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
     protocol
    -0.07
    zte
    -0.07
    andest
    -0.06
     lis
    -0.06
    elda
    -0.06
    protocol
    -0.06
    brero
    -0.06
    aims
    -0.06
    imir
    -0.06
    ¢
    -0.06
    POSITIVE LOGITS
     hút
    0.07
    -build
    0.07
    thane
    0.07
     ì¶ķ
    0.07
     Defence
    0.06
    .getFont
    0.06
    вÑĸ
    0.06
     doctr
    0.06
     Pentagon
    0.06
    uild
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.