© 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. 121655
    Prev
    Next
    INDEX
    Explanations

    references to the progression and performance of athletes over multiple seasons

    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
    uges
    -0.07
    ynamic
    -0.06
    ục
    -0.06
    iores
    -0.06
    ieves
    -0.06
    }());↵
    -0.06
    aye
    -0.06
     Libre
    -0.06
     Sta
    -0.06
    illet
    -0.06
    POSITIVE LOGITS
     career
    0.11
     Career
    0.09
     Careers
    0.08
    Career
    0.08
     careers
    0.08
     carrera
    0.08
    career
    0.08
     kari
    0.07
     profesional
    0.07
     professional
    0.07
    Activations Density 0.020%

    No Known Activations