© 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. 33308
    Prev
    Next
    INDEX
    Explanations

    entrenamiento específico lower body

    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
     hypoth
    -0.11
     Cel
    -0.10
     legit
    -0.09
     Rhe
    -0.09
     cq
    -0.09
    åº
    -0.09
    kaz
    -0.09
     maduras
    -0.09
     Bon
    -0.09
     surviv
    -0.09
    POSITIVE LOGITS
     warm
    0.14
     training
    0.13
     resistance
    0.13
     strength
    0.12
    åĬĽéĩı
    0.12
     dumb
    0.12
     bench
    0.12
     warming
    0.12
     Training
    0.11
     interval
    0.11
    Activations Density 0.109%

    No Known Activations