© 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. 55891
    Prev
    Next
    INDEX
    Explanations

    precocious, lifetime, online, average, proper

    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
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.09
    ostel
    -0.08
     Monter
    -0.08
    LEGRO
    -0.08
    ĮĴ
    -0.08
     Wel
    -0.08
    .isOn
    -0.08
    alace
    -0.07
    ixon
    -0.07
     eventdata
    -0.07
    POSITIVE LOGITS
    ฯ
    0.18
     etc
    0.11
     Cory
    0.10
    etc
    0.10
    id
    0.09
     Jaune
    0.08
     buz
    0.08
    .randomUUID
    0.08
    eniable
    0.08
     Gund
    0.08
    Activations Density 0.101%

    No Known Activations