© 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. 30729
    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
    mitt
    -0.06
    ember
    -0.06
     Jennings
    -0.06
    gt
    -0.06
    inen
    -0.06
    NewLabel
    -0.06
    erez
    -0.06
    iqu
    -0.06
    mente
    -0.06
    isure
    -0.06
    POSITIVE LOGITS
    linky
    0.07
    _WAKE
    0.07
    uell
    0.07
     Mason
    0.07
    atype
    0.07
    Ðĩ
    0.07
    owing
    0.07
    YES
    0.06
    :\/\/
    0.06
     symptom
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.