© 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. 73415
    Prev
    Next
    INDEX
    Explanations

    references to different types of themes or styles in a technical or coded 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
    å½¼
    -0.07
    igli
    -0.07
    astes
    -0.07
    ellar
    -0.07
    rove
    -0.06
     Parsons
    -0.06
    åľ
    -0.06
    chez
    -0.06
    ingle
    -0.06
    :invoke
    -0.06
    POSITIVE LOGITS
    .dart
    0.08
    .jar
    0.08
    .yaml
    0.07
    .py
    0.07
    .png
    0.07
    .php
    0.07
    hle
    0.07
    .jsp
    0.07
    .json
    0.07
    .yml
    0.07
    Activations Density 0.014%

    No Known Activations