© 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. 9-LLAMASCOPE-RES-131K
    11. 98976
    Prev
    Next
    INDEX
    Explanations

    content related to performance evaluation and mistakes 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
    acci
    -0.07
    bac
    -0.07
    вав
    -0.06
    quo
    -0.06
    -columns
    -0.06
     cheered
    -0.06
     sona
    -0.06
     sober
    -0.06
    ozo
    -0.06
     cheer
    -0.06
    POSITIVE LOGITS
    swick
    0.07
    nez
    0.07
    unte
    0.06
    ลล
    0.06
    IFT
    0.06
    ushman
    0.06
     tor
    0.06
    atte
    0.06
    mtree
    0.06
    umen
    0.06
    Activations Density 0.016%

    No Known Activations