© 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 EvalsExportsinterp-engineNEWAPI 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. 70227
    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
    ijken
    -0.10
    Å¡ak
    -0.08
    impan
    -0.07
    жÑĥ
    -0.07
    uffle
    -0.07
    ÄIJT
    -0.07
    ÐIJÑĢÑħÑĸв
    -0.07
    Ø·ÙĨ
    -0.07
    ako
    -0.07
    ÐłÐĿ
    -0.07
    POSITIVE LOGITS
    asar
    0.06
    sd
    0.06
    iban
    0.06
    hid
    0.06
     tub
    0.06
    hashed
    0.05
    erer
    0.05
     Pot
    0.05
    ìĥģ
    0.05
     wish
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.