© 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. 38057
    Prev
    Next
    INDEX
    Explanations

    describing subsequent elements

    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
     -*-č\n
    -0.09
    BOSE
    -0.07
     derec
    -0.07
    .anim
    -0.07
     ür
    -0.07
    adolu
    -0.07
    clc
    -0.07
    ÃŃrk
    -0.07
    .singleton
    -0.07
    AREA
    -0.07
    POSITIVE LOGITS
    zb
    0.07
     Kab
    0.07
    flatten
    0.07
    :;"
    0.07
    rica
    0.07
    лиÑĪком
    0.07
     Ä°mpar
    0.07
    )>>
    0.06
     leng
    0.06
    Intialized
    0.06
    Activations Density 1.237%

    No Known Activations