© 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. 13885
    Prev
    Next
    INDEX
    Explanations

    assistant header

    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
    -Tr
    -0.08
    ower
    -0.08
     orderly
    -0.08
     Schwartz
    -0.08
     dotted
    -0.08
    rax
    -0.08
    omic
    -0.08
     hã
    -0.08
     Mood
    -0.08
     virgin
    -0.08
    POSITIVE LOGITS
    <|end_header_id|>
    0.10
    edio
    0.10
    们
    0.09
    ]:\n\n\n
    0.09
     unb
    0.09
     ><?
    0.09
    iode
    0.09
    witter
    0.08
    .appspot
    0.08
    iline
    0.08
    Activations Density 0.052%

    No Known Activations