© 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. 44603
    Prev
    Next
    INDEX
    Explanations

    leading to definitions or specific content

    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
    s
    -0.24
    a
    -0.19
    i
    -0.16
    d
    -0.15
    n
    -0.15
    t
    -0.13
    m
    -0.13
    T
    -0.12
    M
    -0.12
    c
    -0.12
    POSITIVE LOGITS
    odore
    0.18
    etheless
    0.15
    adays
    0.14
    atre
    0.12
    gether
    0.11
    alog
    0.11
    irs
    0.11
    ÑįÑĤомÑĥ
    0.11
    sWith
    0.10
    tempts
    0.10
    Activations Density 0.085%

    No Known Activations