© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 691
    Prev
    Next
    INDEX
    Explanations

    references to firefighters and fire-related events

    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
    _processors
    -0.08
    ãĤĩ
    -0.08
    itele
    -0.08
    ноз
    -0.08
    icari
    -0.07
     плен
    -0.07
    azor
    -0.07
    ucha
    -0.07
    _Tis
    -0.07
    upa
    -0.07
    POSITIVE LOGITS
     fire
    0.11
     Fire
    0.10
     firefighters
    0.09
    /fire
    0.09
     firefighter
    0.08
    -fire
    0.07
     municipal
    0.07
    Fire
    0.07
     firefight
    0.07
     fires
    0.07
    Activations Density 0.034%

    No Known Activations