© 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 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. 87381
    Prev
    Next
    INDEX
    Explanations

    phrases expressing requests for assistance or support

    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
    pill
    -0.06
    _cum
    -0.06
    ELLOW
    -0.06
    تÙĥ
    -0.06
     ëĭ¨
    -0.06
    á»ĭ
    -0.06
    _defined
    -0.06
    emand
    -0.06
    -bo
    -0.06
    emo
    -0.06
    POSITIVE LOGITS
    ossal
    0.08
    elo
    0.07
     appreciated
    0.07
    pel
    0.07
     greatly
    0.07
    ÑĢÑı
    0.07
    oire
    0.06
     Thank
    0.06
    inar
    0.06
     ontvangst
    0.06
    Activations Density 0.003%

    No Known Activations