© 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. 69654
    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
    ä
    -0.07
    él
    -0.06
    enet
    -0.06
    irsch
    -0.06
    coli
    -0.06
    Boot
    -0.06
    onn
    -0.06
     جاÙĨ
    -0.06
    aid
    -0.06
    ite
    -0.06
    POSITIVE LOGITS
     Municip
    0.07
     cca
    0.07
    omatic
    0.07
    .unbind
    0.07
    .docs
    0.07
     Nes
    0.06
     "-"
    0.06
     "?"
    0.06
    .ali
    0.06
    ÑĩеÑĤ
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.