© 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. 34155
    Prev
    Next
    INDEX
    Explanations

    erstellen

    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
     Luck
    -0.10
     kob
    -0.10
    émon
    -0.10
    hof
    -0.10
    er
    -0.09
    rung
    -0.09
     cones
    -0.09
     Uh
    -0.09
    eri
    -0.08
    erd
    -0.08
    POSITIVE LOGITS
    ehen
    0.13
    klass
    0.13
    ablish
    0.12
    omap
    0.11
    reck
    0.11
    reb
    0.11
    elle
    0.10
    ellt
    0.10
    unken
    0.10
    while
    0.10
    Activations Density 0.016%

    No Known Activations