© 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. 20736
    Prev
    Next
    INDEX
    Explanations

    pronouns followed by actions

    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
     Bere
    -0.08
    ignet
    -0.08
    ovich
    -0.08
    isco
    -0.08
    meer
    -0.08
     increments
    -0.08
    ppe
    -0.08
    instr
    -0.08
    ching
    -0.08
    allen
    -0.08
    POSITIVE LOGITS
     ne
    0.16
     near
    0.11
     sit
    0.11
     continue
    0.10
     sits
    0.10
     sat
    0.10
     stood
    0.10
     approached
    0.10
     lay
    0.10
    ÃŃm
    0.10
    Activations Density 0.022%

    No Known Activations