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

    Neuronpedia

    Jacobian LensNEW
    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. 71185
    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
    èĽ
    -0.08
    733
    -0.08
    å·
    -0.07
    serrat
    -0.07
    enheim
    -0.07
    丶
    -0.07
     ãĢij
    -0.07
    Ä±ÅŁÄ±k
    -0.07
    fout
    -0.07
     saya
    -0.07
    POSITIVE LOGITS
     Eve
    0.06
     Og
    0.06
    ory
    0.06
    wo
    0.06
     Parad
    0.06
    WWW
    0.06
     Moore
    0.05
    LOCKS
    0.05
     NIL
    0.05
     obviously
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.