© 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. 43128
    Prev
    Next
    INDEX
    Explanations

    a/b followed by punctuation

    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
    x
    -0.11
    f
    -0.09
    r
    -0.09
    æĻ´
    -0.09
    jug
    -0.09
    jab
    -0.09
    erti
    -0.08
    st
    -0.08
     PyQt
    -0.08
    al
    -0.08
    POSITIVE LOGITS
    ÂĢÂĢ
    0.12
     Beaver
    0.09
     Chapman
    0.09
    )
    0.09
    zdy
    0.09
    ories
    0.09
    .MoveNext
    0.08
    apg
    0.08
    adium
    0.08
    662
    0.08
    Activations Density 0.068%

    No Known Activations