© 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. 44410
    Prev
    Next
    INDEX
    Explanations

    separate concept or category

    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
    wards
    -0.11
    inqu
    -0.09
    ses
    -0.09
     Hou
    -0.09
    ting
    -0.09
    ÙĨدا
    -0.09
    nze
    -0.09
    imits
    -0.09
    sel
    -0.08
     scoped
    -0.08
    POSITIVE LOGITS
    ively
    0.20
     biá»ĩt
    0.16
     entity
    0.16
     entities
    0.14
    /add
    0.13
    ëĶ°
    0.13
    /dist
    0.13
    /se
    0.12
     apart
    0.12
    /is
    0.11
    Activations Density 0.031%

    No Known Activations