© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 35053
    Prev
    Next
    INDEX
    Explanations

    questions and prompts

    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
    <quote
    -0.10
    íĥĦ
    -0.09
     asc
    -0.09
    ilir
    -0.09
    _Syntax
    -0.09
    _OCCURRED
    -0.08
    ernals
    -0.08
    isy
    -0.08
    ses
    -0.08
     tot
    -0.08
    POSITIVE LOGITS
     request
    0.16
     requests
    0.16
     tasks
    0.15
     statements
    0.14
     task
    0.14
     commands
    0.13
     concerns
    0.12
    ä»»åĬ¡
    0.12
    /or
    0.12
    request
    0.11
    Activations Density 0.056%

    No Known Activations