© 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. 2788
    Prev
    Next
    INDEX
    Explanations

    function hooking

    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
     whom
    -0.10
     pivot
    -0.09
     ref
    -0.09
     import
    -0.09
    ppers
    -0.09
     Cort
    -0.09
    _bindings
    -0.09
    oma
    -0.08
    446
    -0.08
    stantiate
    -0.08
    POSITIVE LOGITS
     override
    0.24
     intercept
    0.24
    override
    0.22
    .Override
    0.21
    \toverride
    0.21
    Override
    0.21
     intercepted
    0.20
     interception
    0.19
     Override
    0.18
     Intercept
    0.18
    Activations Density 0.125%

    No Known Activations