© 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. 44747
    Prev
    Next
    INDEX
    Explanations

    adding -ed or suffix

    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
    utenberg
    -0.09
    canf
    -0.09
    isContained
    -0.09
    ÑĥÑģк
    -0.09
     lint
    -0.09
     Shepherd
    -0.08
     Mein
    -0.08
    \htdocs
    -0.08
     NONINFRINGEMENT
    -0.08
    æĮģ
    -0.08
    POSITIVE LOGITS
     added
    0.34
    added
    0.26
     Added
    0.25
     добав
    0.25
     suffix
    0.24
     aff
    0.24
    Added
    0.24
     addition
    0.23
     attached
    0.23
     onto
    0.23
    Activations Density 0.160%

    No Known Activations