© 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. 27038
    Prev
    Next
    INDEX
    Explanations

    details are about

    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
    emaker
    -0.10
    ìľ¼ë¡ľ
    -0.10
    arium
    -0.10
     detailed
    -0.10
    occ
    -0.10
    esta
    -0.10
    arel
    -0.10
    est
    -0.10
    Äįel
    -0.09
    smith
    -0.09
    POSITIVE LOGITS
    ียà¸Ķ
    0.17
    led
    0.14
    -oriented
    0.12
    loid
    0.10
    iating
    0.10
    ers
    0.10
    leur
    0.10
    sp
    0.10
    /close
    0.09
    页
    0.09
    Activations Density 0.032%

    No Known Activations