© 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. 3680
    Prev
    Next
    INDEX
    Explanations

    references to personal safety and threats

    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
    è¥
    -0.07
    adar
    -0.07
    CHAT
    -0.06
    ÑijÑĢ
    -0.06
    ìĹ¼
    -0.06
    asic
    -0.06
     ascent
    -0.06
    à¸Ńห
    -0.06
    okus
    -0.06
    itech
    -0.06
    POSITIVE LOGITS
     safety
    0.14
     Safety
    0.13
     protection
    0.13
    Safety
    0.12
     Protection
    0.12
     threats
    0.11
    -threat
    0.11
    å®īåħ¨
    0.11
     security
    0.11
    Protection
    0.11
    Activations Density 0.054%

    No Known Activations