© 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
    2. Llama3.3-70B-IT (Instruct)
    3. 50-RESID-POST-GF
    4. 44508
    Prev
    Next
    INDEX
    Explanations

    fragrance, fragile, fragment

    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
     Hann
    -0.11
    vely
    -0.10
    inder
    -0.09
    isiyle
    -0.09
    iale
    -0.09
     uncon
    -0.09
    loh
    -0.09
    prise
    -0.09
    .EntityFramework
    -0.09
     GObject
    -0.09
    POSITIVE LOGITS
    rances
    0.17
    rant
    0.16
    rance
    0.13
    менÑĤ
    0.12
     Frag
    0.12
    gle
    0.12
    ility
    0.12
     frag
    0.12
    ments
    0.12
    ged
    0.12
    Activations Density 0.007%

    No Known Activations