© 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. 26846
    Prev
    Next
    INDEX
    Explanations

    references to individuals with the last name "Kol" or similar variations

    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
    /sweetalert
    -0.08
    ties
    -0.08
    ippi
    -0.07
    a
    -0.07
    erot
    -0.07
    ÑĨÑĸ
    -0.07
    Ñĸз
    -0.07
    ihan
    -0.07
    ceae
    -0.07
    eon
    -0.07
    POSITIVE LOGITS
    λοÏį
    0.07
    aybe
    0.06
     disciplines
    0.06
    uj
    0.06
     Gel
    0.06
     Cent
    0.06
    cent
    0.06
    ative
    0.06
    ________________________________________________________________
    0.06
    aylight
    0.06
    Activations Density 0.008%

    No Known Activations