© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 105027
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax elements, specifically PHP code

    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
    linger
    -0.07
    velt
    -0.07
    at
    -0.06
    aris
    -0.06
    ul
    -0.06
    cre
    -0.06
    åģ
    -0.06
     activity
    -0.06
     Balk
    -0.06
    rir
    -0.06
    POSITIVE LOGITS
     endif
    0.10
     Hath
    0.08
    endregion
    0.07
    #endregion
    0.07
    ("</
    0.07
     endregion
    0.07
    oreach
    0.07
    endforeach
    0.07
    onces
    0.07
    abeth
    0.07
    Activations Density 0.018%

    No Known Activations