© 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. 18549
    Prev
    Next
    INDEX
    Explanations

    significant aspects of sports gameplay, particularly substitutions and tactical changes

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    pedia
    -0.07
    iesel
    -0.07
    анка
    -0.07
    ugu
    -0.07
     اÙĤ
    -0.07
    ipur
    -0.07
    anke
    -0.07
    itele
    -0.06
     nackte
    -0.06
    unker
    -0.06
    POSITIVE LOGITS
     replace
    0.10
     replacing
    0.10
     replacement
    0.09
     replacements
    0.09
     replaced
    0.09
     Replace
    0.09
     replaces
    0.08
     Replacement
    0.08
    replace
    0.08
    Replace
    0.08
    Activations Density 0.013%

    No Known Activations