© 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. 41283
    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
    Ú©ÙĪر
    -0.07
    iglia
    -0.07
    uelles
    -0.07
    adro
    -0.07
    leet
    -0.07
    erais
    -0.07
    ÐIJÑĢÑħÑĸв
    -0.07
    ÎłÏģο
    -0.07
    боÑĤ
    -0.07
    ardash
    -0.07
    POSITIVE LOGITS
    oph
    0.06
     Whisper
    0.06
    ema
    0.06
    ilo
    0.06
    isch
    0.06
    arte
    0.05
     *(*
    0.05
     Weinstein
    0.05
    wang
    0.05
    nic
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.