© 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. 74893
    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
     pitch
    -0.08
     {{--<
    -0.08
    osl
    -0.07
    ONUS
    -0.07
    vented
    -0.07
    onsense
    -0.06
    γά
    -0.06
    imas
    -0.06
    Ùİا
    -0.06
    .Misc
    -0.06
    POSITIVE LOGITS
    erializer
    0.06
    WithError
    0.06
     vids
    0.06
     intermedi
    0.06
     Fallen
    0.06
     Bound
    0.06
    vore
    0.06
    -Speed
    0.06
    orney
    0.06
    ioni
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.