© 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. 22239
    Prev
    Next
    INDEX
    Explanations

    sets of components and procedures

    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
     Mature
    -0.09
    onom
    -0.09
     tantal
    -0.09
     interstate
    -0.09
     Stub
    -0.09
    wu
    -0.09
     indiv
    -0.08
     Mech
    -0.08
    spa
    -0.08
    DD
    -0.08
    POSITIVE LOGITS
    /or
    0.14
     sometimes
    0.10
     actions
    0.10
    ptest
    0.10
     often
    0.09
     accompanying
    0.09
     usually
    0.09
    ueue
    0.09
    lor
    0.09
     rules
    0.09
    Activations Density 0.183%

    No Known Activations