© 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. 34585
    Prev
    Next
    INDEX
    Explanations

    person following articles

    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
    EMPLARY
    -0.10
    /WebAPI
    -0.10
     Cumhur
    -0.09
    groupon
    -0.09
    >NN
    -0.09
    antic
    -0.09
     ëĭ¤ìļ´ë°Ľê¸°
    -0.09
     пÑĢоÑĦеÑģÑģионалÑĮ
    -0.09
     lesb
    -0.09
    taboola
    -0.09
    POSITIVE LOGITS
     Mesh
    0.11
     Smith
    0.11
    ald
    0.10
     Person
    0.10
     record
    0.09
    rette
    0.09
    Smith
    0.09
     profiles
    0.09
     records
    0.09
    ohn
    0.09
    Activations Density 0.330%

    No Known Activations