© 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. 42740
    Prev
    Next
    INDEX
    Explanations

    instructions and building

    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
    iego
    -0.10
    endi
    -0.09
    end
    -0.09
     fullPath
    -0.09
     os
    -0.09
     inst
    -0.08
     Prism
    -0.08
    opr
    -0.08
    eki
    -0.08
     Lloyd
    -0.08
    POSITIVE LOGITS
    ains
    0.15
    aining
    0.15
    uct
    0.14
     dá»±ng
    0.13
    ucción
    0.13
    s
    0.12
    iction
    0.12
    uir
    0.12
    éĢł
    0.12
    uido
    0.11
    Activations Density 0.026%

    No Known Activations