© 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. 44742
    Prev
    Next
    INDEX
    Explanations

    numbers after 10

    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
    iff
    -0.11
    ernet
    -0.11
    ayan
    -0.10
    IFF
    -0.09
    upt
    -0.09
    enco
    -0.09
    outs
    -0.09
    ened
    -0.09
    ivol
    -0.09
    zed
    -0.08
    POSITIVE LOGITS
    857
    0.11
    030
    0.11
    atted
    0.10
    ilet
    0.09
    060
    0.09
    simp
    0.09
    italize
    0.09
    isms
    0.09
    _redis
    0.09
    ateurs
    0.08
    Activations Density 0.062%

    No Known Activations