© 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. 99034
    Prev
    Next
    INDEX
    Explanations

    scientific variables and constants related to physics and mathematics

    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
    ÙĤÙĦ
    -0.07
    chest
    -0.07
    misc
    -0.07
    ieg
    -0.07
    еÑģÑı
    -0.07
    rawn
    -0.07
    вали
    -0.07
    uesto
    -0.06
    avec
    -0.06
    aterno
    -0.06
    POSITIVE LOGITS
    acos
    0.07
    梨
    0.07
    /Runtime
    0.06
    à¥ĥ
    0.06
    ea
    0.06
    elve
    0.06
     agency
    0.06
    apter
    0.06
    инÑĥв
    0.06
     accounting
    0.06
    Activations Density 0.085%

    No Known Activations