© 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. 78628
    Prev
    Next
    INDEX
    Explanations

    concepts related to decision-making and the implications of choices

    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
    eid
    -0.08
    onical
    -0.07
     vind
    -0.07
    ilin
    -0.07
    elp
    -0.07
     plá
    -0.07
    arella
    -0.07
    .builders
    -0.07
    itol
    -0.07
    clist
    -0.07
    POSITIVE LOGITS
     something
    0.09
     thing
    0.08
    thing
    0.07
    something
    0.07
     situation
    0.07
    (thing
    0.07
     outcomes
    0.07
     things
    0.07
     Thing
    0.06
     phenomenon
    0.06
    Activations Density 0.048%

    No Known Activations