© 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 EvalsExportsinterp-engineNEWAPI 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. 5202
    Prev
    Next
    INDEX
    Explanations

    expressions of uncertainty or questioning

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

    Function words that indicate uncertainty, conditionality, or appear in question-answer contexts.

    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
    ropolis
    -0.07
    okane
    -0.07
    isel
    -0.06
    *pow
    -0.06
    uen
    -0.06
    antis
    -0.06
    anye
    -0.06
    aho
    -0.06
    ometr
    -0.06
    tü
    -0.06
    POSITIVE LOGITS
     answer
    0.08
     Answer
    0.08
     nowhere
    0.07
     nothing
    0.07
    çŃĶæ¡Ī
    0.07
     clue
    0.07
    answer
    0.07
    çŃĶ
    0.07
     plenty
    0.07
    çĶļ
    0.07
    Activations Density 0.059%

    No Known Activations