© 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. 3169
    Prev
    Next
    INDEX
    Explanations

    the das

    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
    iasi
    -0.11
    ----------</
    -0.10
    'gc
    -0.10
    âĸį
    -0.09
    edenÃŃ
    -0.08
    hiro
    -0.08
    _OPTS
    -0.08
    ongyang
    -0.08
    ----</
    -0.08
    KANJI
    -0.08
    POSITIVE LOGITS
     latter
    0.19
     both
    0.12
     ëijĺ
    0.11
     beiden
    0.10
     ambos
    0.10
    both
    0.10
     versa
    0.10
     beide
    0.09
     Both
    0.09
    å®ĥ们
    0.09
    Activations Density 0.127%

    No Known Activations