© 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. 61725
    Prev
    Next
    INDEX
    Explanations

    linear, Kemal, reverse

    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
    ain
    -0.10
    ory
    -0.10
    ating
    -0.10
    ange
    -0.10
    ise
    -0.10
    ated
    -0.09
    fr
    -0.09
     pend
    -0.09
    iver
    -0.09
    anka
    -0.09
    POSITIVE LOGITS
    inear
    0.11
     Kemal
    0.10
    undra
    0.10
    emouth
    0.09
    yalty
    0.09
    .styleable
    0.09
     Madd
    0.09
    ¿ł
    0.09
     reverse
    0.09
    oeff
    0.09
    Activations Density 0.029%

    No Known Activations