© 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. 123253
    Prev
    Next
    INDEX
    Explanations

    terms related to peak experiences and maximum values

    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
    ÅĤaw
    -0.07
    iji
    -0.07
    ">ÃĹ</
    -0.07
    ấn
    -0.07
    ucch
    -0.07
    ExecutionContext
    -0.06
    pedia
    -0.06
    νοÏĤ
    -0.06
     fod
    -0.06
    Ñĥв
    -0.06
    POSITIVE LOGITS
    Reached
    0.10
    peak
    0.10
     reached
    0.09
     peak
    0.09
    ãĥĥãĤ·ãĥ¥
    0.08
    /Peak
    0.08
     Reached
    0.08
    Peak
    0.08
     Peak
    0.08
    ima
    0.07
    Activations Density 0.064%

    No Known Activations