© 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. 9-LLAMASCOPE-RES-131K
    11. 97383
    Prev
    Next
    INDEX
    Explanations

    programming language constructs and functions related to data fetching and component lifecycle

    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
    æľĭ
    -0.08
    женÑĮ
    -0.08
    /gin
    -0.07
    ERCHANT
    -0.07
    ienda
    -0.07
    emme
    -0.07
    ImageContext
    -0.07
    otionEvent
    -0.07
    /callback
    -0.07
    itbart
    -0.07
    POSITIVE LOGITS
     Vance
    0.07
    acre
    0.06
    borough
    0.06
     MyBase
    0.05
    amus
    0.05
    ëĭ¥
    0.05
    init
    0.05
     disposition
    0.05
    iane
    0.05
    43
    0.05
    Activations Density 0.014%

    No Known Activations