© 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. 38677
    Prev
    Next
    INDEX
    Explanations

    the name of

    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
    åIJį
    -0.16
     name
    -0.15
     names
    -0.14
     åIJį
    -0.12
    ByName
    -0.12
     Namen
    -0.12
    names
    -0.11
     tên
    -0.10
    389
    -0.10
    _name
    -0.10
    POSITIVE LOGITS
     streets
    0.13
     unborn
    0.10
    ecz
    0.09
     variables
    0.09
     ÑĦайла
    0.09
     Streets
    0.09
    stre
    0.09
     file
    0.09
     пеÑĢемен
    0.09
    akes
    0.09
    Activations Density 0.127%

    No Known Activations