Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 5609
    Prev
    Next
    INDEX
    Explanations

    the occurrence of the name "Boyd" and variations of the word "dealing" in context

    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
    duct
    -0.06
    eya
    -0.06
    ovie
    -0.06
     dic
    -0.06
    exus
    -0.06
    bers
    -0.06
     Zeit
    -0.06
     ë¶Ļ
    -0.06
    BED
    -0.06
    è¶³
    -0.06
    POSITIVE LOGITS
    ston
    0.11
    linky
    0.09
    voj
    0.08
    shr
    0.08
    ÑĨов
    0.07
     ฿
    0.07
    ham
    0.07
    ÚĺÙĩ
    0.07
    zig
    0.07
    dech
    0.07
    Activations Density 0.001%

    No Known Activations