© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 15981
    Prev
    Next
    INDEX
    Explanations

    references to violence and its implications

    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
    nga
    -0.09
    ossible
    -0.08
    dlg
    -0.08
    Invariant
    -0.08
    ubit
    -0.08
    loha
    -0.08
    ibbon
    -0.08
    maze
    -0.08
    rolled
    -0.08
    ÅĻiv
    -0.08
    POSITIVE LOGITS
    iveness
    0.08
    uous
    0.07
    ous
    0.07
    ometown
    0.07
    625
    0.07
    ive
    0.07
    358
    0.06
    /or
    0.06
    339
    0.06
    /security
    0.06
    Activations Density 0.015%

    No Known Activations