© 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. 63296
    Prev
    Next
    INDEX
    Explanations

    scripting or programming functions and methods

    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
    ÑĤеÑĢи
    -0.07
    üb
    -0.07
    ãĥ«ãĥī
    -0.07
    گاÙĨ
    -0.07
    å¥
    -0.07
    NavController
    -0.06
     isAuthenticated
    -0.06
    esor
    -0.06
    ±
    -0.06
     tuz
    -0.06
    POSITIVE LOGITS
     Sentry
    0.07
    onis
    0.06
    ìĹħì²´
    0.06
    bra
    0.06
     Invitation
    0.06
    민주
    0.06
    bras
    0.06
    eve
    0.06
    ied
    0.05
     focus
    0.05
    Activations Density 0.011%

    No Known Activations