© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 26901
    Prev
    Next
    INDEX
    Explanations

    abbreviations followed by specific words

    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
    ew
    -0.16
    ame
    -0.13
    ews
    -0.12
    onde
    -0.11
    g
    -0.11
    era
    -0.11
    crm
    -0.11
    d
    -0.11
    eko
    -0.11
    dev
    -0.11
    POSITIVE LOGITS
    ุษย
    0.13
    ัà¸ģà¸ĩาà¸Ļ
    0.12
    side
    0.12
    alysis
    0.12
    ัà¸ļสà¸Ļ
    0.11
    ep
    0.11
    ucle
    0.11
    rat
    0.10
    apped
    0.10
    ec
    0.10
    Activations Density 0.100%

    No Known Activations