© 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. 20451
    Prev
    Next
    INDEX
    Explanations

    vanes or blades

    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
     angled
    -0.11
     tapered
    -0.10
     Graz
    -0.10
     spindle
    -0.09
     elong
    -0.09
    .neo
    -0.09
     pump
    -0.09
     pumps
    -0.09
    INLINE
    -0.09
     reels
    -0.09
    POSITIVE LOGITS
     gro
    0.20
     teeth
    0.16
    gro
    0.16
     conc
    0.15
    Gro
    0.15
     profile
    0.14
     Gro
    0.14
     tips
    0.14
     Conc
    0.13
     groove
    0.13
    Activations Density 0.072%

    No Known Activations