© 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. 82566
    Prev
    Next
    INDEX
    Explanations

    action verbs that indicate making choices or taking actions

    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
    uese
    -0.08
    lund
    -0.07
    refixer
    -0.07
    -il
    -0.07
    ãĢ
    -0.07
    ackers
    -0.07
    -UA
    -0.07
    acker
    -0.07
    UIT
    -0.07
    aylight
    -0.07
    POSITIVE LOGITS
    ings
    0.10
    able
    0.08
    ÂŃing
    0.07
     thereby
    0.07
    ability
    0.07
     them
    0.07
    ollo
    0.07
    ingly
    0.07
     it
    0.06
    ing
    0.06
    Activations Density 0.103%

    No Known Activations