© 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. 55597
    Prev
    Next
    INDEX
    Explanations

    extent or magnitude

    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
    ness
    -0.11
    ier
    -0.11
    ern
    -0.11
    ery
    -0.10
     enough
    -0.10
    ie
    -0.10
    athon
    -0.10
    ertainment
    -0.10
    eper
    -0.10
    lier
    -0.10
    POSITIVE LOGITS
    -than
    0.27
    anging
    0.23
     than
    0.22
    than
    0.19
    /sm
    0.18
     вÑģего
    0.17
    ange
    0.17
     niż
    0.16
    most
    0.15
    _than
    0.15
    Activations Density 0.021%

    No Known Activations