© 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. 14424
    Prev
    Next
    INDEX
    Explanations

    strategic discussions around game plans and player performance in sports

    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
    ango
    -0.06
    938
    -0.06
    raž
    -0.06
     Kend
    -0.06
    odom
    -0.06
     CSR
    -0.06
    íĥģ
    -0.06
     Provid
    -0.05
     performing
    -0.05
    genden
    -0.05
    POSITIVE LOGITS
     schemes
    0.08
     scheme
    0.08
     Scheme
    0.08
    chemes
    0.07
    scheme
    0.07
    Scheme
    0.07
    ATOM
    0.07
     chữ
    0.07
     æ·
    0.07
    cheme
    0.07
    Activations Density 0.030%

    No Known Activations