© 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 EvalsExportsAPI 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. 82975
    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
    uden
    -0.08
    uthor
    -0.07
    lew
    -0.07
    ź
    -0.06
    éħį
    -0.06
    nameof
    -0.06
     ÙħاÙĨ
    -0.06
    discord
    -0.06
    ازÛĮ
    -0.06
     Ñģка
    -0.06
    POSITIVE LOGITS
    Äįer
    0.07
    ģm
    0.07
    .echo
    0.06
    eydi
    0.06
    occo
    0.06
     Accum
    0.06
     Ned
    0.06
    ynes
    0.06
    á»ĥn
    0.06
    OURS
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.