© 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. 55376
    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
    aba
    -0.06
    amiliar
    -0.06
     /
    -0.06
     familiar
    -0.06
     selfish
    -0.06
     pinch
    -0.06
     ultimately
    -0.06
    ,
    -0.05
    ç¼
    -0.05
    endency
    -0.05
    POSITIVE LOGITS
    omain
    0.08
    çĬ
    0.08
    رÙĪت
    0.07
     neod
    0.07
    redo
    0.07
    .neo
    0.07
    ữa
    0.07
    UNET
    0.07
    skyt
    0.07
    Æ°á»Łng
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.