© 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. 107293
    Prev
    Next
    INDEX
    Explanations

    specific numerical identifiers or references, often in a coding or technical context

    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
    ỳ
    -0.07
    ive
    -0.06
    inand
    -0.06
    ิà¸ŀ
    -0.06
    endon
    -0.06
    stanov
    -0.06
     prem
    -0.06
    Ả
    -0.05
    xmin
    -0.05
    =Value
    -0.05
    POSITIVE LOGITS
    onest
    0.07
    unken
    0.06
    etc
    0.06
    еÑĢж
    0.06
    ÑģÑĥÑĤ
    0.06
    leet
    0.06
    anza
    0.06
    aub
    0.06
    odzi
    0.06
    midd
    0.06
    Activations Density 0.003%

    No Known Activations