© 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. 42596
    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
    olic
    -0.07
     ABC
    -0.06
     Sawyer
    -0.06
    ickerView
    -0.06
    lasses
    -0.06
     abc
    -0.06
    ABC
    -0.06
     Pun
    -0.06
    à¤ľà¤¨
    -0.05
    chem
    -0.05
    POSITIVE LOGITS
    اط
    0.07
    SCII
    0.07
    _lift
    0.07
    çŃĴ
    0.07
    _ctxt
    0.07
    anine
    0.06
     kesin
    0.06
    zion
    0.06
    WithPath
    0.06
    uxt
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.