© 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. 117110
    Prev
    Next
    INDEX
    Explanations

    terms related to fear and safety in a crisis context

    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
    ardo
    -0.07
    andaÅŁ
    -0.07
    anke
    -0.06
    894
    -0.06
    gfx
    -0.06
    оÑĢон
    -0.06
    VELO
    -0.06
    EIF
    -0.06
    esium
    -0.06
    icon
    -0.06
    POSITIVE LOGITS
     crew
    0.09
     Ping
    0.08
     Crew
    0.08
    crew
    0.08
     Safety
    0.08
     safety
    0.07
    afety
    0.07
    è§
    0.07
     vessel
    0.06
     Deck
    0.06
    Activations Density 0.002%

    No Known Activations