© 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. 104248
    Prev
    Next
    INDEX
    Explanations

    discussions about psychological concepts and societal issues

    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
    .bunifuFlatButton
    -0.10
    ">//
    -0.08
    ÅĻejmÄĽ
    -0.07
    jiÅ¡tÄĽnÃŃ
    -0.07
    é§ħå¾ĴæŃ©
    -0.07
     оÑĤли
    -0.07
    важа
    -0.07
    ë¿IJ
    -0.07
    ormsg
    -0.07
    .panelControl
    -0.07
    POSITIVE LOGITS
     absolutely
    0.08
     eigentlich
    0.08
     exactly
    0.07
     United
    0.07
     absolute
    0.07
    lah
    0.06
     воÑĤ
    0.06
    æĪĸèĢħ
    0.06
    对äºİ
    0.06
     абÑģолÑİÑĤно
    0.06
    Activations Density 0.055%

    No Known Activations