© 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. 62746
    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
    ÃĹ↵↵
    -0.07
     Foley
    -0.07
     esto
    -0.06
     Jennings
    -0.06
    Ngh
    -0.06
     ppl
    -0.06
    ÌĤ
    -0.06
    ibu
    -0.06
     RESP
    -0.06
    Îĸ
    -0.06
    POSITIVE LOGITS
    ummings
    0.08
    gaard
    0.07
    uche
    0.07
    каÑĤ
    0.06
    emi
    0.06
    iversite
    0.06
    ervo
    0.06
    sein
    0.06
    ardon
    0.06
    ankind
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.