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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT (Instruct)
    5. 50-RESID-POST-GF
    7. 38045
    Prev
    Next
    INDEX
    Explanations

    response generation

    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
     suic
    -0.09
    edin
    -0.09
     Surre
    -0.09
    apture
    -0.08
    atak
    -0.08
     Dah
    -0.08
    ô
    -0.08
     phys
    -0.08
    IRD
    -0.08
    omain
    -0.08
    POSITIVE LOGITS
     Response
    0.11
     response
    0.10
     odpovÄĽ
    0.10
     Dün
    0.09
     answer
    0.09
    çŃĶæ¡Ī
    0.08
     Dexter
    0.08
     $#
    0.08
    borough
    0.08
    iou
    0.08
    Activations Density 0.044%

    No Known Activations