© 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. 41966
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and notations related to functions or equations

    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
    oten
    -0.07
    olini
    -0.07
    reen
    -0.06
    ednou
    -0.06
    ayla
    -0.06
    kowski
    -0.06
    ê¹
    -0.06
    azzi
    -0.06
    uard
    -0.06
    INUX
    -0.06
    POSITIVE LOGITS
    496
    0.07
    erin
    0.07
    vore
    0.07
    ModelProperty
    0.07
    977
    0.06
    ptrdiff
    0.06
    anc
    0.06
    \Field
    0.06
    oney
    0.06
     Mess
    0.06
    Activations Density 0.043%

    No Known Activations