© 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. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 22353
    Prev
    Next
    INDEX
    Explanations

    risk assessment

    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
    cul
    -0.09
    arpa
    -0.09
    achs
    -0.09
    ä¸įå¾Ĺ
    -0.09
     ãĤĿ
    -0.09
     mildly
    -0.08
    plib
    -0.08
     dele
    -0.08
    omas
    -0.08
     Rounded
    -0.08
    POSITIVE LOGITS
     risk
    0.18
     risks
    0.17
     greatest
    0.17
     Ris
    0.16
    ãĥªãĤ¹
    0.14
     ris
    0.14
     greater
    0.14
    ris
    0.14
     associated
    0.13
     highest
    0.13
    Activations Density 0.062%

    No Known Activations