© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 22915
    Prev
    Next
    INDEX
    Explanations

    wp-content, sg, dt, lb, ff, bg codes

    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
    a
    -0.14
    s
    -0.13
    l
    -0.12
    y
    -0.12
    e
    -0.11
    yyy
    -0.11
    t
    -0.11
    rans
    -0.11
    r
    -0.10
    oft
    -0.10
    POSITIVE LOGITS
    .wikipedia
    0.11
    'er
    0.10
    iture
    0.10
    ps
    0.10
    bs
    0.09
    quo
    0.09
    .linkedin
    0.09
    .fre
    0.09
    itures
    0.09
    ote
    0.09
    Activations Density 0.145%

    No Known Activations