© 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. 63269
    Prev
    Next
    INDEX
    Explanations

    references to teams and their performance in sports contexts

    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
    572
    -0.06
    .debian
    -0.06
    ç±
    -0.06
    γκο
    -0.06
    ãĢģç§ģ
    -0.06
    ASM
    -0.06
    mess
    -0.06
    hammer
    -0.06
    .drawLine
    -0.06
    agen
    -0.06
    POSITIVE LOGITS
    elan
    0.06
    isti
    0.06
    ocoder
    0.06
    zens
    0.06
    ony
    0.06
    IENTATION
    0.06
    ipo
    0.06
    aur
    0.06
    εί
    0.06
     otherwise
    0.06
    Activations Density 0.026%

    No Known Activations