© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 34721
    Prev
    Next
    INDEX
    Explanations

    orbit around stars

    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
    meteor
    -0.12
     planetary
    -0.11
    Meteor
    -0.11
     Meteor
    -0.11
     lunar
    -0.10
     meteor
    -0.09
    kos
    -0.09
    assis
    -0.09
    OTO
    -0.09
     legislation
    -0.09
    POSITIVE LOGITS
     sun
    0.42
     Sun
    0.42
    Sun
    0.34
    sun
    0.34
     SUN
    0.28
    _sun
    0.27
    .sun
    0.25
     Ñģолн
    0.21
     Suns
    0.21
     Sunni
    0.20
    Activations Density 0.045%

    No Known Activations