© 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. 79311
    Prev
    Next
    INDEX
    Explanations

    song titles and references to music and lyrics

    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
     series
    -0.06
    ÑĢиз
    -0.06
    åĩ¡
    -0.06
     Ãľn
    -0.06
    eldorf
    -0.06
    ç±į
    -0.06
    iscard
    -0.06
    bjerg
    -0.06
     дела
    -0.06
    edia
    -0.06
    POSITIVE LOGITS
     Wik
    0.09
    æ·
    0.07
    orias
    0.07
    imizer
    0.07
    ding
    0.07
    HQ
    0.07
     fik
    0.07
    ãĤ¼
    0.07
     wik
    0.06
    unal
    0.06
    Activations Density 0.015%

    No Known Activations