© 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. 2064
    Prev
    Next
    INDEX
    Explanations

    nature of the risks

    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
    .Formatter
    -0.09
    rames
    -0.09
    Sharper
    -0.09
    EMPLARY
    -0.09
    /*č\n
    -0.08
    ¶Į
    -0.08
    <|begin_of_text|>
    -0.08
    .Dictionary
    -0.08
     -*-č\n
    -0.08
    \tHX
    -0.08
    POSITIVE LOGITS
    ï¿
    0.10
    v
    0.08
    a
    0.08
    l
    0.08
    c
    0.08
    p
    0.08
    0.08
    b
    0.08
    is
    0.08
    ch
    0.08
    Activations Density 0.012%

    No Known Activations