© 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. 29530
    Prev
    Next
    INDEX
    Explanations

    instances of the word "what" and related phrases questioning situations or 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
     spontaneous
    -0.07
    важа
    -0.07
    inos
    -0.06
    .mvp
    -0.06
     spont
    -0.06
    .pattern
    -0.06
    isas
    -0.06
    utura
    -0.06
    illez
    -0.06
    hev
    -0.06
    POSITIVE LOGITS
     causes
    0.10
     cause
    0.09
     Causes
    0.09
     causing
    0.09
     causa
    0.08
     Cause
    0.07
     Explanation
    0.07
    cause
    0.07
    Cause
    0.07
    thumbnails
    0.07
    Activations Density 0.018%

    No Known Activations