© 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. 15-LLAMASCOPE-RES-131K
    11. 86681
    Prev
    Next
    INDEX
    Explanations

    components related to date and time picking in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code fragments from web development files, primarily highlighting HTML tags, attributes, JavaScript initializations, and UI component libraries.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    ossier
    -0.09
    лага
    -0.08
    upo
    -0.07
    reffen
    -0.07
    ebi
    -0.07
    kowski
    -0.06
    acus
    -0.06
    umbo
    -0.06
    uegos
    -0.06
     sami
    -0.06
    POSITIVE LOGITS
     chop
    0.06
    ForObject
    0.06
    .forRoot
    0.06
     managed
    0.06
    626
    0.06
    lla
    0.06
    ảng
    0.06
    _sun
    0.05
     Buccane
    0.05
    WithContext
    0.05
    Activations Density 0.037%

    No Known Activations