© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 13949
    Prev
    Next
    INDEX
    Explanations

    acronyms ending in s

    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
    w
    -0.16
    p
    -0.16
    c
    -0.16
    u
    -0.16
    on
    -0.16
    l
    -0.15
    h
    -0.15
    al
    -0.15
    à¸Ļ
    -0.15
    Ùĩ
    -0.15
    POSITIVE LOGITS
    rams
    0.11
    rate
    0.11
    lian
    0.10
    river
    0.10
    Ùħا
    0.10
    itr
    0.10
    ranÃŃ
    0.10
    ides
    0.10
    rama
    0.09
    rej
    0.09
    Activations Density 0.125%

    No Known Activations