© 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. 13761
    Prev
    Next
    INDEX
    Explanations

    assistant response start

    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
     Yue
    -0.10
     Geile
    -0.09
    ipse
    -0.09
     erotik
    -0.09
    .Enqueue
    -0.09
     embod
    -0.09
    /lab
    -0.08
    ÏĨÏĮ
    -0.08
     PTR
    -0.08
     Mighty
    -0.08
    POSITIVE LOGITS
     mere
    0.09
     Dit
    0.09
     Wit
    0.09
    plr
    0.09
     greatness
    0.08
    rou
    0.08
    orry
    0.08
    <|end_header_id|>
    0.08
     succ
    0.08
     anarchist
    0.08
    Activations Density 0.162%

    No Known Activations