© 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. 18778
    Prev
    Next
    INDEX
    Explanations

    negations and phrases expressing doubt or denial

    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
    .offset
    -0.08
    ingle
    -0.07
    alement
    -0.07
    assic
    -0.07
    ãģĭãĤı
    -0.07
    ections
    -0.07
    окÑĢем
    -0.07
    è¿ĺæĺ¯
    -0.07
     либо
    -0.07
    lang
    -0.06
    POSITIVE LOGITS
    resh
    0.06
    uft
    0.06
    addock
    0.06
    ebin
    0.06
    landa
    0.06
     often
    0.06
    ernen
    0.06
     nearly
    0.05
     usually
    0.05
    Neutral
    0.05
    Activations Density 0.035%

    No Known Activations