© 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. 2945
    Prev
    Next
    INDEX
    Explanations

    references to attacks and perpetrators in various contexts

    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
    onta
    -0.07
     Mounted
    -0.07
    hift
    -0.07
    ishop
    -0.07
    enton
    -0.06
    ellas
    -0.06
    oons
    -0.06
     wishes
    -0.06
    piel
    -0.06
    abyrin
    -0.06
    POSITIVE LOGITS
     organizer
    0.07
     planning
    0.07
     aborted
    0.07
    addtogroup
    0.06
    Planning
    0.06
     Abort
    0.06
     operatives
    0.06
     plotting
    0.06
     abort
    0.06
    odor
    0.06
    Activations Density 0.003%

    No Known Activations