© 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. 35571
    Prev
    Next
    INDEX
    Explanations

    change in state or intensity

    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
    ively
    -0.12
    teil
    -0.10
    /from
    -0.10
    side
    -0.09
    612
    -0.09
    alet
    -0.09
    te
    -0.09
    aley
    -0.09
    iveness
    -0.09
    abin
    -0.09
    POSITIVE LOGITS
    /stretch
    0.14
    /light
    0.12
    ning
    0.12
    ening
    0.12
    nement
    0.12
    ess
    0.12
    /stream
    0.12
    -up
    0.11
    /we
    0.11
     further
    0.11
    Activations Density 0.057%

    No Known Activations