© 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. 17-LLAMASCOPE-RES-131K
    11. 39805
    Prev
    Next
    INDEX
    Explanations

    references to personal experiences or testimonials related to family or cultural identities

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

    A person's name followed by a colon to indicate the beginning of their speech in a transcript or dialogue format.

    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
    ETO
    -0.08
    ãĥªãĤ¢
    -0.08
    anca
    -0.07
    ãģļ
    -0.07
    διά
    -0.07
    ãĤīãģĦ
    -0.07
    sworth
    -0.07
     SPACE
    -0.07
    amba
    -0.07
    atism
    -0.07
    POSITIVE LOGITS
    idget
    0.06
     Brom
    0.06
    ivol
    0.06
     "
    0.06
    hai
    0.05
     [
    0.05
     yes
    0.05
    ivar
    0.05
     Mess
    0.05
    н
    0.05
    Activations Density 0.043%

    No Known Activations