© 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. 38071
    Prev
    Next
    INDEX
    Explanations

    following accounting steps

    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
     hon
    -0.10
    /conf
    -0.10
     depreci
    -0.09
    ŀæĢ§
    -0.09
     Laf
    -0.09
     cole
    -0.09
    rese
    -0.09
    iese
    -0.09
     Dom
    -0.09
     receipts
    -0.09
    POSITIVE LOGITS
     journal
    0.16
    journal
    0.13
     deb
    0.13
    ÂĢÂĢ
    0.13
     Journal
    0.13
    Journal
    0.12
    debit
    0.11
     recording
    0.11
     contra
    0.11
    fixtures
    0.10
    Activations Density 0.055%

    No Known Activations