© 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. 16289
    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
    год
    -0.06
    bé
    -0.06
    inae
    -0.06
    mtx
    -0.06
    otes
    -0.06
    StartPosition
    -0.06
     kov
    -0.06
     ~=
    -0.06
    кав
    -0.06
    ég
    -0.06
    POSITIVE LOGITS
    izon
    0.07
    StackNavigator
    0.07
    erver
    0.07
     tslib
    0.07
    izont
    0.07
    .opend
    0.06
    zion
    0.06
    lington
    0.06
    onomies
    0.06
    _lazy
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.