© 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. 38606
    Prev
    Next
    INDEX
    Explanations

    identity and access management

    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
    éł
    -0.10
     identities
    -0.09
     yaw
    -0.09
     idiots
    -0.09
     Jefferson
    -0.09
    -Israel
    -0.09
     Kendall
    -0.08
     Hitler
    -0.08
    oru
    -0.08
    orman
    -0.08
    POSITIVE LOGITS
     defaultMessage
    0.14
    \GeneratedValue
    0.13
    GeneratedValue
    0.11
    chwitz
    0.10
    achuset
    0.10
     expression
    0.10
    .cloudflare
    0.09
    doch
    0.09
    odate
    0.08
     Seymour
    0.08
    Activations Density 0.062%

    No Known Activations