© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 30329
    Prev
    Next
    INDEX
    Explanations

    a fierce, skilled

    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
    defense
    -0.11
    .metamodel
    -0.10
    esel
    -0.10
    hiba
    -0.09
     Victim
    -0.09
     defence
    -0.09
     defense
    -0.09
    _EOL
    -0.09
     Worst
    -0.09
    ursal
    -0.09
    POSITIVE LOGITS
     elite
    0.15
     skill
    0.14
     skilled
    0.14
     feared
    0.13
     Elite
    0.13
     fears
    0.13
    loy
    0.13
    elite
    0.13
     fer
    0.12
     skills
    0.12
    Activations Density 0.088%

    No Known Activations