© 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. 126931
    Prev
    Next
    INDEX
    Explanations

    themes related to decision-making and selecting options

    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
    /Instruction
    -0.07
    contre
    -0.07
     Îķλλην
    -0.07
    inth
    -0.07
    foon
    -0.07
    ẩy
    -0.07
    à¤Ĺर
    -0.07
    ook
    -0.07
    isay
    -0.07
    .yy
    -0.07
    POSITIVE LOGITS
     single
    0.08
    single
    0.07
    ancel
    0.07
     only
    0.07
     limit
    0.06
    chia
    0.06
     one
    0.06
     merely
    0.06
     singular
    0.06
    list
    0.06
    Activations Density 0.006%

    No Known Activations