© 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. 89870
    Prev
    Next
    INDEX
    Explanations

    programming terms related to queries and parameters

    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
    ombat
    -0.08
    anja
    -0.08
    asje
    -0.08
    arity
    -0.08
    arias
    -0.08
    andler
    -0.07
    á»ķ
    -0.07
    vider
    -0.07
    umbnail
    -0.07
    ereotype
    -0.07
    POSITIVE LOGITS
    (s
    0.06
     variable
    0.06
    sg
    0.06
     Blanch
    0.06
     pron
    0.06
     Bowman
    0.06
     s
    0.06
    ocos
    0.06
    æĻ
    0.06
     variables
    0.06
    Activations Density 0.002%

    No Known Activations