© 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. 2497
    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
     Glam
    -0.06
    Extras
    -0.06
     familiar
    -0.06
     glamour
    -0.06
    úsqueda
    -0.06
    bubble
    -0.06
     Bulk
    -0.06
    ÙĪاء
    -0.06
    Lite
    -0.06
     haar
    -0.06
    POSITIVE LOGITS
     guys
    0.08
     gentleman
    0.07
    çĤī
    0.07
     dudes
    0.07
    erosis
    0.07
     barber
    0.07
     guy
    0.07
    нок
    0.07
     dad
    0.07
     men
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.