© 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. 64285
    Prev
    Next
    INDEX
    Explanations

    suspicious activity

    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
     çĿ
    -0.09
    FFFF
    -0.09
    ï½ī
    -0.08
    hed
    -0.08
    Roz
    -0.08
    avo
    -0.08
    (Dialog
    -0.08
    dbg
    -0.08
    deme
    -0.08
    Ñĸно
    -0.08
    POSITIVE LOGITS
     activity
    0.67
    activity
    0.50
     Activity
    0.49
    æ´»åĬ¨
    0.44
     actividad
    0.44
    æ´»åĭķ
    0.43
    Activity
    0.42
     active
    0.42
     activities
    0.41
    _activity
    0.37
    Activations Density 0.126%

    No Known Activations