© 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. 9960
    Prev
    Next
    INDEX
    Explanations

    over the

    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
     darüber
    -0.15
    IFO
    -0.09
    CCR
    -0.09
    uro
    -0.09
    ä¹İ
    -0.09
     overhead
    -0.09
     zoekt
    -0.08
    irl
    -0.08
    ongo
    -0.08
    che
    -0.08
    POSITIVE LOGITS
     course
    0.16
     heads
    0.14
     shoulder
    0.14
     rooft
    0.14
     objections
    0.14
     shoulders
    0.13
     threshold
    0.11
     span
    0.11
     Shoulder
    0.11
     horizon
    0.11
    Activations Density 0.072%

    No Known Activations