© 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 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. 84196
    Prev
    Next
    INDEX
    Explanations

    references to stealing or theft

    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
    iesz
    -0.07
    757
    -0.06
    209
    -0.06
    quiring
    -0.06
    avi
    -0.06
    Å¡ov
    -0.06
    asty
    -0.06
    orta
    -0.06
    icÃŃ
    -0.06
    quier
    -0.06
    POSITIVE LOGITS
     away
    0.09
     khá»ıi
    0.08
     thunder
    0.08
     from
    0.07
     ÙħÙĨÙĩا
    0.07
     secrets
    0.07
    afone
    0.07
     Blizzard
    0.06
    :UITableView
    0.06
     Dak
    0.06
    Activations Density 0.025%

    No Known Activations