© 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. 91669
    Prev
    Next
    INDEX
    Explanations

    affirmative phrases indicating assistance or guarantees

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    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
    indow
    -0.07
    497
    -0.06
     Seal
    -0.06
    reet
    -0.06
    áct
    -0.06
     people
    -0.06
    ÑıÑĩи
    -0.06
    adian
    -0.05
    ovy
    -0.05
    buie
    -0.05
    POSITIVE LOGITS
    ê³
    0.08
    avr
    0.07
    atisch
    0.07
    ůj
    0.07
    ÏĦιÏĥ
    0.07
    assis
    0.06
    mith
    0.06
    asje
    0.06
    ISIBLE
    0.06
     you
    0.06
    Activations Density 0.013%

    No Known Activations