© 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. 76330
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "look" and its variations

    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
     ÑĤов
    -0.07
    ctal
    -0.07
    ektor
    -0.07
    tober
    -0.06
    uben
    -0.06
    itre
    -0.06
    éģĵ
    -0.06
    owo
    -0.06
    ichi
    -0.06
    away
    -0.06
    POSITIVE LOGITS
    Suc
    0.07
    wnd
    0.06
    CurrentValue
    0.06
    INED
    0.06
    bb
    0.06
     Suc
    0.06
    LOOK
    0.06
    oom
    0.06
    ůž
    0.06
    ENTION
    0.06
    Activations Density 0.022%

    No Known Activations