© 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. 69495
    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
     Tw
    -0.06
    uder
    -0.06
    eres
    -0.06
    357
    -0.06
    orge
    -0.06
     Ara
    -0.05
     ок
    -0.05
     impunity
    -0.05
    pmat
    -0.05
     present
    -0.05
    POSITIVE LOGITS
     Trafford
    0.07
    raya
    0.07
    à¤Ĺढ
    0.07
    reak
    0.06
    uell
    0.06
    elta
    0.06
    ucci
    0.06
    ourg
    0.06
    _nth
    0.06
    Subset
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.