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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Llama3.3-70B-IT
    3. 50-RESID-POST-GF
    4. 37600
    Prev
    Next
    INDEX
    Explanations

    people's names

    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
     Lep
    -0.09
    icut
    -0.09
     chase
    -0.08
     Helm
    -0.08
     Pett
    -0.08
    meteor
    -0.08
     Shot
    -0.08
     domaine
    -0.08
    æµ
    -0.08
     Scotia
    -0.08
    POSITIVE LOGITS
     trainer
    0.10
    âĦĸâĦĸ
    0.10
     Barrier
    0.10
    trainer
    0.10
     Christ
    0.09
     stable
    0.09
     j
    0.09
    надлеж
    0.09
     Mong
    0.09
    bled
    0.09
    Activations Density 0.007%

    No Known Activations