© 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. 38035
    Prev
    Next
    INDEX
    Explanations

    any followed by qualifier

    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
     various
    -0.10
     Duy
    -0.09
     a
    -0.09
    ubar
    -0.08
     same
    -0.08
    ActionCreators
    -0.08
     ones
    -0.08
    angler
    -0.08
    baugh
    -0.08
    ä¸Ģä¸ĭ
    -0.08
    POSITIVE LOGITS
    ting
    0.21
     kind
    0.21
    kind
    0.20
    other
    0.20
    THING
    0.19
    /all
    0.18
    ones
    0.17
     thing
    0.17
     other
    0.16
    Thing
    0.16
    Activations Density 0.080%

    No Known Activations