© 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. 38478
    Prev
    Next
    INDEX
    Explanations

    specific car features and color descriptions

    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
     lah
    -0.07
    ogan
    -0.07
    reds
    -0.07
    enga
    -0.06
    stem
    -0.06
    agne
    -0.06
    //{{
    -0.06
    hol
    -0.06
    idel
    -0.06
    umas
    -0.06
    POSITIVE LOGITS
    Ø·ÙĨ
    0.07
    icont
    0.06
     Certified
    0.06
    usted
    0.06
    ÙĪÙĬÙĥ
    0.06
     IDictionary
    0.06
    ä¼Ļ
    0.06
    çŁ¢
    0.06
    ãĥ³ãĥĦ
    0.06
    atri
    0.06
    Activations Density 0.002%

    No Known Activations