© 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. 62479
    Prev
    Next
    INDEX
    Explanations

    instructions related to applying graphics or decals

    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
     boycott
    -0.07
    acket
    -0.06
    åĿª
    -0.06
    isos
    -0.06
    isko
    -0.06
    umo
    -0.06
    oil
    -0.06
    иÑģк
    -0.06
    wj
    -0.06
    .getMap
    -0.06
    POSITIVE LOGITS
     finish
    0.10
     finishing
    0.09
     final
    0.09
     finished
    0.09
     finalize
    0.08
     Final
    0.08
    Final
    0.08
     completed
    0.08
    assen
    0.07
     Finished
    0.07
    Activations Density 0.010%

    No Known Activations