Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 40382
    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
    ylene
    -0.06
    ICA
    -0.06
     contribution
    -0.06
    stor
    -0.06
    iron
    -0.06
    Iron
    -0.06
    ılıç
    -0.05
    CD
    -0.05
     dialog
    -0.05
     Sta
    -0.05
    POSITIVE LOGITS
     handjob
    0.07
    nds
    0.07
    utzer
    0.07
     Certain
    0.07
    OfClass
    0.07
    ζα
    0.07
    .less
    0.07
    Ticker
    0.06
     iterating
    0.06
    ereo
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.