© 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. 70071
    Prev
    Next
    INDEX
    Explanations

    expressions related to personal aspirations and desires

    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
    eyse
    -0.08
    ÅĽci
    -0.08
     tolua
    -0.07
    (æľ¨
    -0.07
     kayıt
    -0.07
    braco
    -0.07
    çĽijåIJ¬é¡µéĿ¢
    -0.07
    ÙĨاء
    -0.07
    erva
    -0.07
     stere
    -0.07
    POSITIVE LOGITS
     fucks
    0.07
     fucked
    0.07
     cunt
    0.07
     fucking
    0.07
     fuck
    0.06
    ór
    0.06
     hadn
    0.06
    lying
    0.06
     cocks
    0.06
     boyfriend
    0.06
    Activations Density 0.020%

    No Known Activations