© 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. 69007
    Prev
    Next
    INDEX
    Explanations

    references to academic and professional experiences

    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
    jsc
    -0.08
    haft
    -0.07
    stad
    -0.07
    ожд
    -0.07
    bjerg
    -0.07
     Wald
    -0.07
     ÙħØ«
    -0.06
    anova
    -0.06
     bard
    -0.06
    gart
    -0.06
    POSITIVE LOGITS
     Westbrook
    0.08
     cot
    0.06
     spent
    0.06
    onto
    0.06
    INGTON
    0.06
     Trace
    0.06
     palate
    0.06
     Samp
    0.06
     Research
    0.06
    ARIO
    0.06
    Activations Density 0.006%

    No Known Activations