© 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. 4480
    Prev
    Next
    INDEX
    Explanations

    sets of analytics, calculations, examples, reactions, steps, equations, classes

    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
     aspects
    -0.13
    æĸ¹éĿ¢
    -0.11
     amounts
    -0.10
     audiences
    -0.10
    ftware
    -0.10
    ¶Į
    -0.10
     crews
    -0.09
     populations
    -0.09
    æŃ
    -0.09
    ides
    -0.08
    POSITIVE LOGITS
     proportions
    0.13
    adesh
    0.11
     possibilities
    0.10
    ailles
    0.09
     events
    0.09
     proportion
    0.09
    ulia
    0.09
    .Serializable
    0.09
     Boyle
    0.08
     tests
    0.08
    Activations Density 0.155%

    No Known Activations