© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 18817
    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
    Negative Logits
    rine
    -0.07
    gio
    -0.06
    ↵
    -0.06
    :↵
    -0.05
    30
    -0.05
    ibus
    -0.05
    icros
    -0.05
    idot
    -0.05
     Yol
    -0.05
    :
    -0.05
    POSITIVE LOGITS
    rowsable
    0.09
    à¥Ģà¤Ĩà¤Ī
    0.08
     داخ
    0.08
    inkel
    0.08
    ichtig
    0.07
    Indented
    0.07
    OfSize
    0.07
    -indent
    0.07
    çıŃ
    0.07
     вÑĸÑĤ
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.