© 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. 41859
    Prev
    Next
    INDEX
    Explanations

    mathematical concepts and terminology related to theories and methods in physics

    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
    IMO
    -0.08
    onus
    -0.07
     ziy
    -0.07
    suz
    -0.06
    Ä°ÅŁ
    -0.06
    umo
    -0.06
    ifu
    -0.06
    ccd
    -0.06
    بار
    -0.06
    Circular
    -0.06
    POSITIVE LOGITS
    OTTOM
    0.07
     YYS
    0.07
    sworth
    0.07
     applicable
    0.07
    .SizeType
    0.07
     applied
    0.06
    ellido
    0.06
    QUIRE
    0.06
    ually
    0.06
    .wikipedia
    0.06
    Activations Density 0.100%

    No Known Activations