© 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. 87772
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "whether" indicating uncertainty or choices related to individuals' situations and abilities

    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
    roys
    -0.07
    dge
    -0.06
    krom
    -0.06
    रण
    -0.06
    apur
    -0.06
    eker
    -0.06
    	Con
    -0.06
    ãĥŃãĥ³
    -0.06
    agra
    -0.06
    cad
    -0.06
    POSITIVE LOGITS
     or
    0.10
     Formal
    0.08
    ëĵł
    0.08
     formal
    0.07
    Exact
    0.07
    è¿ĺæĺ¯
    0.07
    whether
    0.07
     whether
    0.07
     ever
    0.07
    ãģ¾ãģŁãģ¯
    0.07
    Activations Density 0.017%

    No Known Activations