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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 84756
    Prev
    Next
    INDEX
    Explanations

    instances of parentheses and associated content, specifically in the context of song titles or performances

    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
    æĺĮ
    -0.07
    baÅŁ
    -0.07
     offsetof
    -0.07
    ngr
    -0.07
     имÑĥ
    -0.07
    (/*
    -0.07
    maz
    -0.07
    drs
    -0.07
     ÙħÛĮÙĦادÛĮ
    -0.07
    itals
    -0.06
    POSITIVE LOGITS
    _firestore
    0.07
    acers
    0.06
    anon
    0.06
     gameTime
    0.06
     McDonald
    0.06
    Question
    0.06
    (Unknown
    0.06
    ideo
    0.06
    utterstock
    0.06
     privately
    0.05
    Activations Density 0.017%

    No Known Activations