© 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. 61586
    Prev
    Next
    INDEX
    Explanations

    Clannad, CLIP, named entities

    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
     classname
    -0.10
    ibase
    -0.09
    arrass
    -0.09
    ISTR
    -0.09
    -lfs
    -0.08
    enic
    -0.08
    theid
    -0.08
     spare
    -0.08
    lify
    -0.08
     cá
    -0.08
    POSITIVE LOGITS
     cl
    0.36
     Cl
    0.31
    Cl
    0.29
    (cl
    0.26
     CL
    0.26
    .cl
    0.26
    (Cl
    0.23
    cl
    0.23
    .CL
    0.22
     кл
    0.21
    Activations Density 0.081%

    No Known Activations