© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 125169
    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
    illez
    -0.07
    coles
    -0.07
    emma
    -0.07
    ango
    -0.07
    EdgeInsets
    -0.07
    ediator
    -0.06
    afone
    -0.06
    aphael
    -0.06
    hots
    -0.06
    utherford
    -0.06
    POSITIVE LOGITS
     ourselves
    0.07
     our
    0.07
    omen
    0.06
    ((↵
    0.06
    ìļ°ë¦¬
    0.06
    umuz
    0.06
    ÃŃrk
    0.06
    vo
    0.06
     éc
    0.06
     tonight
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.