© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 81881
    Prev
    Next
    INDEX
    Explanations

    terms specifically related to science and scientific discourse

    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
    tra
    -0.07
    uls
    -0.07
    ri
    -0.07
    malink
    -0.06
    itudes
    -0.06
    uter
    -0.06
    ly
    -0.06
    çµ
    -0.06
    ing
    -0.06
    lander
    -0.06
    POSITIVE LOGITS
    /math
    0.07
    зÑı
    0.07
    /engine
    0.07
    earer
    0.07
    arily
    0.07
    andle
    0.07
    -fiction
    0.06
    ayla
    0.06
    izoph
    0.06
    /stat
    0.06
    Activations Density 0.014%

    No Known Activations