© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 96157
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude and polite inquiries

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    Punctuation marks (periods, commas, exclamation points) and pronouns in customer service or forum response contexts, often appearing at the end of sentences or phrases in direct communication with customers or users.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219
    Triggered 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
    Negative Logits
    acom
    -0.07
    gaard
    -0.06
    *)"
    -0.06
    imag
    -0.06
     injunction
    -0.06
    ادÙĬØ©
    -0.06
     Jung
    -0.05
    lect
    -0.05
     stagn
    -0.05
     вÑģÑĤ
    -0.05
    POSITIVE LOGITS
    indow
    0.08
    raki
    0.07
     hare
    0.07
    διο
    0.07
    oproject
    0.06
    θο
    0.06
    .Factory
    0.06
    ç¶
    0.06
    raith
    0.06
    ajar
    0.06
    Activations Density 0.011%

    No Known Activations