© 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. 42455
    Prev
    Next
    INDEX
    Explanations

    terms related to spinal cord injuries and medical research associated with them

    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
    izer
    -0.07
    åīĤ
    -0.07
    eps
    -0.06
     ابÙĪ
    -0.06
    egin
    -0.06
    abinet
    -0.06
     /*!↵
    -0.06
    strain
    -0.06
    ambda
    -0.06
    egree
    -0.06
    POSITIVE LOGITS
     injury
    0.07
     relay
    0.07
    æIJį
    0.07
    /sp
    0.06
     damage
    0.06
     Injury
    0.06
     insult
    0.06
    ¼åIJĪ
    0.06
    ench
    0.06
    rosse
    0.06
    Activations Density 0.002%

    No Known Activations