© 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. 34493
    Prev
    Next
    INDEX
    Explanations

    tels que, Tante, tasse, TLM

    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
    ree
    -0.12
    LOGGER
    -0.11
    oft
    -0.11
    ime
    -0.10
    imei
    -0.10
    ableView
    -0.10
    mpz
    -0.09
    agt
    -0.09
    agg
    -0.09
     Vernon
    -0.09
    POSITIVE LOGITS
    such
    0.12
    ref
    0.11
    artin
    0.11
    apis
    0.11
    ëĭ¹
    0.10
    is
    0.10
    akt
    0.10
    ardi
    0.10
    rec
    0.10
     testimon
    0.10
    Activations Density 0.026%

    No Known Activations