© 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. 1727
    Prev
    Next
    INDEX
    Explanations

    type of company that is

    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
     [+
    -0.09
     âĢı
    -0.09
     unm
    -0.08
     адже
    -0.08
    906
    -0.08
    vik
    -0.08
     --
    -0.08
    ancel
    -0.08
    \-
    -0.08
    enÃŃ
    -0.08
    POSITIVE LOGITS
    [c
    0.14
     Template
    0.14
    [n
    0.11
    âĢħ
    0.10
    .Template
    0.09
    anes
    0.09
    Template
    0.09
    /|
    0.09
    .ogg
    0.09
     citation
    0.08
    Activations Density 0.151%

    No Known Activations