© 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. 42446
    Prev
    Next
    INDEX
    Explanations

    references to vitamins and their relevance to health conditions, particularly Multiple Sclerosis

    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
    onet
    -0.07
    ndl
    -0.07
    abo
    -0.07
    ww
    -0.06
    asco
    -0.06
    Dims
    -0.06
    sites
    -0.06
    orca
    -0.06
    stral
    -0.06
    å·
    -0.06
    POSITIVE LOGITS
    /her
    0.07
    ssql
    0.07
     correct
    0.07
    ombo
    0.07
     Wenger
    0.07
     deficiency
    0.07
     repl
    0.06
    arshal
    0.06
    láš
    0.06
    theValue
    0.06
    Activations Density 0.006%

    No Known Activations