© 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. 5561
    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
    _Construct
    -0.07
    ÙıÙĪا
    -0.07
     *\
    -0.07
    ÛĮÙĨÚ©
    -0.07
    ãĤ¯ãĥŃ
    -0.07
    تاب
    -0.07
    subtract
    -0.07
    нÑĸÑĪ
    -0.07
    Parms
    -0.06
    isas
    -0.06
    POSITIVE LOGITS
     profile
    0.07
     paternal
    0.07
    ako
    0.07
    hattan
    0.06
    cn
    0.06
    101
    0.06
    zy
    0.06
    profile
    0.06
     MaterialApp
    0.06
    essen
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.