© 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 (Instruct)
    5. 50-RESID-POST-GF
    7. 38036
    Prev
    Next
    INDEX
    Explanations

    large language model

    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
    ity
    -0.10
    oter
    -0.09
    ady
    -0.09
     subs
    -0.09
    rob
    -0.09
    icult
    -0.09
    479
    -0.09
    ter
    -0.08
    yor
    -0.08
    ulations
    -0.08
    POSITIVE LOGITS
     model
    0.13
     models
    0.12
    模åŀĭ
    0.12
    /small
    0.11
    'gc
    0.11
     модели
    0.10
     modèle
    0.10
    kah
    0.10
    agues
    0.09
     modele
    0.09
    Activations Density 0.016%

    No Known Activations