© 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. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 24386
    Prev
    Next
    INDEX
    Explanations

    can be life-threatening

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.3-70B-IT @ 50-resid-post-gf
    Configuration
    Goodfire/Llama-3.3-70B-Instruct-SAE-l50/Llama-3.3-70B-Instruct-SAE-l50.pt
    Prompts (Dashboard)
    10,000 prompts, 128 tokens each
    Dataset (Dashboard)
    lmsys/lmsys-chat-1m
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     diseases
    -0.10
    SENS
    -0.10
     Diseases
    -0.10
     SMB
    -0.10
    çĹħ
    -0.10
     Hurt
    -0.10
     ger
    -0.10
    Òij
    -0.09
     wreck
    -0.09
    Ñģки
    -0.09
    POSITIVE LOGITS
     coma
    0.21
     organ
    0.20
     shock
    0.20
     death
    0.18
     Shock
    0.17
     collapse
    0.16
     organs
    0.15
    death
    0.14
    Shock
    0.14
    coma
    0.14
    Activations Density 0.055%

    No Known Activations