© 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. 17-LLAMASCOPE-RES-131K
    6. 129054
    Prev
    Next
    INDEX
    Explanations

    events related to accidents or incidents

    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
    pii
    -0.06
     Shooter
    -0.06
     massac
    -0.06
    ange
    -0.06
    /Table
    -0.06
    ighth
    -0.06
     Barnett
    -0.06
    iris
    -0.06
    stro
    -0.05
    jn
    -0.05
    POSITIVE LOGITS
     happened
    0.08
     xảy
    0.08
     occurred
    0.07
     happening
    0.07
    onaut
    0.07
    ToProps
    0.07
     occurring
    0.06
     happen
    0.06
    igon
    0.06
    ató
    0.06
    Activations Density 0.013%

    No Known Activations