© 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. 44692
    Prev
    Next
    INDEX
    Explanations

    bending, squatting, reaching

    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
    867
    -0.10
     Clim
    -0.09
    857
    -0.09
     shoulder
    -0.09
    rette
    -0.09
     climbs
    -0.09
     swim
    -0.09
    ornado
    -0.09
    icus
    -0.09
     bumps
    -0.09
    POSITIVE LOGITS
     sto
    0.42
     bent
    0.39
     bending
    0.39
     bend
    0.38
     Bend
    0.34
     bends
    0.32
     squat
    0.32
     Sto
    0.31
    sto
    0.27
     Bent
    0.26
    Activations Density 0.049%

    No Known Activations