© 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. 55014
    Prev
    Next
    INDEX
    Explanations

    programming terms and mathematical expressions

    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
    ¦¬
    -0.07
    (strict
    -0.07
    endar
    -0.07
     Bris
    -0.07
     Bilim
    -0.07
    InSection
    -0.07
    Ñĥг
    -0.07
    оÑĢод
    -0.07
    _bindings
    -0.07
    ofire
    -0.07
    POSITIVE LOGITS
     n
    0.06
     rap
    0.06
    inh
    0.06
     Rap
    0.06
    loo
    0.06
    ä¸įäºĨ
    0.06
     only
    0.06
     all
    0.05
     in
    0.05
     and
    0.05
    Activations Density 0.043%

    No Known Activations