© 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. 34521
    Prev
    Next
    INDEX
    Explanations

    and followed by noun

    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
    oge
    -0.10
    RefCount
    -0.09
    alla
    -0.09
    undy
    -0.09
     Derm
    -0.08
    ListOf
    -0.08
    InitialState
    -0.08
    .resp
    -0.08
    iga
    -0.08
    stm
    -0.08
    POSITIVE LOGITS
    /or
    0.22
    erson
    0.17
    amp
    0.16
    rogen
    0.14
    /OR
    0.14
    apos
    0.13
    rog
    0.12
    ean
    0.11
    phans
    0.10
    reas
    0.10
    Activations Density 0.074%

    No Known Activations