© 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. 77097
    Prev
    Next
    INDEX
    Explanations

    references to personal responsibility and preparation

    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
     Gamb
    -0.06
    ICODE
    -0.06
    memiÅŁ
    -0.06
    kv
    -0.06
    games
    -0.06
    IFO
    -0.06
    ocab
    -0.06
     budouc
    -0.06
    ivities
    -0.06
    ingleton
    -0.05
    POSITIVE LOGITS
     aim
    0.10
     goal
    0.08
     decisions
    0.08
     choice
    0.07
     choices
    0.07
     odds
    0.07
    å²³
    0.07
     primary
    0.07
    mere
    0.07
    NotFoundError
    0.07
    Activations Density 0.015%

    No Known Activations