© 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. 38570
    Prev
    Next
    INDEX
    Explanations

    keywords related to artistic and healing practices

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    ogl
    -0.07
    akra
    -0.07
     Lager
    -0.07
    岡
    -0.07
    san
    -0.07
    efs
    -0.07
    á»Ńi
    -0.07
     é«
    -0.07
    jur
    -0.07
    GRAM
    -0.06
    POSITIVE LOGITS
     corporate
    0.07
     write
    0.07
     custom
    0.07
     occasional
    0.06
     Corporate
    0.06
     speaking
    0.06
     writing
    0.06
    ghost
    0.06
     teaching
    0.06
     Write
    0.06
    Activations Density 0.038%

    No Known Activations