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

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 88973
    Prev
    Next
    INDEX
    Explanations

    instances of conversational interactions or dialogue

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

    Names of speakers or interviewers followed by punctuation like colon, or words indicating a question is being asked to someone within an interview or dialogue 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
    nun
    -0.07
    ippi
    -0.06
    ubi
    -0.06
     eleg
    -0.06
    ãĥģãĥ¥
    -0.06
    tte
    -0.06
    orum
    -0.06
    -Jun
    -0.06
    iteli
    -0.06
    çıł
    -0.06
    POSITIVE LOGITS
     questions
    0.11
    asking
    0.10
     asking
    0.10
     asked
    0.10
     interviewer
    0.10
     interview
    0.09
     ask
    0.09
     asks
    0.09
    questions
    0.09
     Interview
    0.09
    Activations Density 0.075%

    No Known Activations