© 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. 57751
    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
    -0.06
     +
    -0.06
     ->
    -0.06
     previously
    -0.06
    &gt
    -0.06
    agon
    -0.05
    xad
    -0.05
    .cc
    -0.05
     @
    -0.05
     reliant
    -0.05
    POSITIVE LOGITS
    antro
    0.08
    CallCheck
    0.08
    浩
    0.08
    .Undef
    0.07
    oggler
    0.07
    OGLE
    0.07
    ôi
    0.07
    anship
    0.07
    /WebAPI
    0.07
     âĨĴ↵↵
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.