© 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. 12049
    Prev
    Next
    INDEX
    Explanations

    more concise, natural, readable

    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
    å¼ĭ
    -0.11
     succinct
    -0.10
    .sav
    -0.10
    ç§
    -0.09
     simpl
    -0.09
    ẫu
    -0.09
     intellect
    -0.09
    emarks
    -0.08
     Polar
    -0.08
     CGI
    -0.08
    POSITIVE LOGITS
     flow
    0.18
    flow
    0.18
    -flow
    0.17
    æµģ
    0.16
     flowing
    0.16
     flowed
    0.16
     professional
    0.15
    Flow
    0.15
    gram
    0.15
     reads
    0.15
    Activations Density 0.099%

    No Known Activations