© 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. 49571
    Prev
    Next
    INDEX
    Explanations

    haz una

    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
     bytesRead
    -0.10
    aggio
    -0.09
     Brend
    -0.09
    tras
    -0.08
     Bere
    -0.08
    makta
    -0.08
    Highlighted
    -0.08
    hn
    -0.08
    asant
    -0.08
     continent
    -0.08
    POSITIVE LOGITS
    ienda
    0.14
    OwnProperty
    0.12
     clic
    0.12
     Herald
    0.11
    athon
    0.11
    ifax
    0.10
    lope
    0.10
    eln
    0.10
    ardless
    0.09
    phalt
    0.09
    Activations Density 0.064%

    No Known Activations