Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Llama3.3-70B-IT (Instruct)
    3. 50-RESID-POST-GF
    4. 44840
    Prev
    Next
    INDEX
    Explanations

    person's work or identity

    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
     famously
    -0.09
    896
    -0.09
    etsk
    -0.09
     Funk
    -0.09
     Roles
    -0.09
     Kunst
    -0.08
     bi
    -0.08
    arts
    -0.08
     kun
    -0.08
    /result
    -0.08
    POSITIVE LOGITS
     produces
    0.15
     releasing
    0.14
     produce
    0.14
     producing
    0.13
     gained
    0.13
     creates
    0.13
     gaining
    0.12
     whose
    0.12
     experiment
    0.12
     signed
    0.11
    Activations Density 0.133%

    No Known Activations