© 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. 23739
    Prev
    Next
    INDEX
    Explanations

    multiple choice

    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
    emes
    -0.11
    okino
    -0.09
    ALLOC
    -0.09
    åIJĦç§į
    -0.09
    icable
    -0.09
    sm
    -0.09
    ValueType
    -0.08
    ings
    -0.08
    ohana
    -0.08
    /tos
    -0.08
    POSITIVE LOGITS
     sclerosis
    0.33
    -choice
    0.18
    clerosis
    0.18
    /single
    0.14
    oma
    0.13
    Choice
    0.13
    IPLE
    0.13
     Choice
    0.13
    iating
    0.12
     intellig
    0.12
    Activations Density 0.029%

    No Known Activations