© 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. 22246
    Prev
    Next
    INDEX
    Explanations

    the volume or size

    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
     derivation
    -0.16
     asympt
    -0.11
     caus
    -0.11
     equivalent
    -0.10
    851
    -0.10
     ell
    -0.09
    ikel
    -0.08
    .conf
    -0.08
     clip
    -0.08
     deriv
    -0.08
    POSITIVE LOGITS
    ore
    0.20
    ORE
    0.14
    orem
    0.14
     set
    0.13
    urgy
    0.10
    :animated
    0.10
    alk
    0.10
     entries
    0.10
     suprem
    0.10
    entries
    0.09
    Activations Density 0.137%

    No Known Activations