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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 126883
    Prev
    Next
    INDEX
    Explanations

    occurrences of numbers and mathematical symbols

    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
    issen
    -0.07
    íıIJ
    -0.07
    etter
    -0.07
    تاÙĨ
    -0.07
     Sanayi
    -0.07
     zv
    -0.07
    ysl
    -0.07
    .keywords
    -0.07
    _________________↵↵
    -0.07
    owski
    -0.06
    POSITIVE LOGITS
     Tweets
    0.07
    å³
    0.06
    ayne
    0.06
     im
    0.06
    ega
    0.06
    786
    0.06
    ami
    0.06
    by
    0.06
    604
    0.06
    99
    0.05
    Activations Density 0.009%

    No Known Activations