© 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. 39826
    Prev
    Next
    INDEX
    Explanations

    K words

    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
    anela
    -0.12
    obus
    -0.11
    iá»ĩt
    -0.11
    uala
    -0.11
    peg
    -0.11
    rupa
    -0.10
    odable
    -0.10
    _RF
    -0.10
    reator
    -0.10
    DidLoad
    -0.10
    POSITIVE LOGITS
    ran
    0.12
    link
    0.12
    ac
    0.11
    abin
    0.11
    isu
    0.10
    apse
    0.10
    ose
    0.10
    edo
    0.10
    eview
    0.10
    iez
    0.10
    Activations Density 0.045%

    No Known Activations