© 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. 120321
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and symbols associated with 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
    ä¸Ī
    -0.08
    .jsoup
    -0.07
    alarm
    -0.07
    lady
    -0.07
    Alarm
    -0.07
    klady
    -0.06
    ultipart
    -0.06
    esseract
    -0.06
    ennon
    -0.06
    otine
    -0.06
    POSITIVE LOGITS
    raction
    0.08
     servo
    0.07
     Optical
    0.07
    inar
    0.07
     optical
    0.07
     Bracket
    0.07
     Gim
    0.06
     Gig
    0.06
     pupil
    0.06
     Cousins
    0.06
    Activations Density 0.037%

    No Known Activations