© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 86100
    Prev
    Next
    INDEX
    Explanations

    rhetorical questions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Question marks at the end of phrases that introduce a definition or explanation of a concept, typically in an educational or informational context.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    amo
    -0.07
    ór
    -0.06
    alse
    -0.06
    iginal
    -0.06
     spl
    -0.06
     иÑģÑħод
    -0.06
    alth
    -0.06
    _CAST
    -0.06
    vest
    -0.06
     Spl
    -0.05
    POSITIVE LOGITS
     definition
    0.10
    Definition
    0.10
     Definition
    0.10
    definition
    0.09
     definitions
    0.08
    istrovstvÃŃ
    0.08
    -definition
    0.08
    ãģ¨ãģ¯
    0.07
    Definitions
    0.07
     âĹĦ
    0.07
    Activations Density 0.035%

    No Known Activations