© 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. 14295
    Prev
    Next
    INDEX
    Explanations

    themes of vulnerability and personal struggle in music contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    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
     sed
    -0.07
     Sed
    -0.07
     unmanned
    -0.06
     zoekt
    -0.06
    oris
    -0.06
    _txn
    -0.06
    ìĿ´ìĹIJ
    -0.06
    åĤ
    -0.06
    .Commit
    -0.06
    ÏĥÏĦημα
    -0.06
    POSITIVE LOGITS
    ÌĨ
    0.08
    eyh
    0.08
    pek
    0.07
    202
    0.07
    ibold
    0.07
    etim
    0.07
     equally
    0.07
    INCLUDED
    0.06
    eti
    0.06
    Äįet
    0.06
    Activations Density 0.063%

    No Known Activations