© 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. 22604
    Prev
    Next
    INDEX
    Explanations

    running and hiding

    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
     walks
    -0.12
    æŃ©
    -0.11
     shri
    -0.11
     circum
    -0.10
     walking
    -0.10
     walk
    -0.10
     electric
    -0.09
     walked
    -0.09
    yw
    -0.09
     stepping
    -0.09
    POSITIVE LOGITS
     running
    0.24
     outr
    0.21
     Running
    0.21
    Running
    0.20
     chạy
    0.20
    .running
    0.20
     RUNNING
    0.20
    è·ij
    0.20
     ran
    0.20
    running
    0.19
    Activations Density 0.019%

    No Known Activations