© 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. 77419
    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
    ocommerce
    -0.06
    óż
    -0.06
     Pipes
    -0.06
    ltk
    -0.06
    ìī¬
    -0.06
    ulan
    -0.06
    ecess
    -0.05
     indefinite
    -0.05
    enth
    -0.05
    645
    -0.05
    POSITIVE LOGITS
    iers
    0.07
    EdgeInsets
    0.07
    iera
    0.07
    ï¼ł
    0.07
    yll
    0.07
    .MixedReality
    0.07
    orts
    0.07
    /backend
    0.07
    mpp
    0.06
    illon
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.