© 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. 53736
    Prev
    Next
    INDEX
    Explanations

    phrases expressing honesty or truthfulness

    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
    aver
    -0.07
    assage
    -0.06
    uest
    -0.06
    Ìĥ
    -0.06
     ÐŁÐ¾Ñĩ
    -0.06
    occo
    -0.06
    ilian
    -0.06
    اÙĤ
    -0.06
    оÑĢож
    -0.06
    illard
    -0.06
    POSITIVE LOGITS
     quite
    0.07
    aken
    0.07
    .about
    0.07
     confession
    0.07
    ÙģاÙĤ
    0.07
    yy
    0.07
    anos
    0.06
    ylene
    0.06
     strictly
    0.06
    ulen
    0.06
    Activations Density 0.005%

    No Known Activations