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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 756
    Prev
    Next
    INDEX
    Explanations

    coref resolution and computer cores

    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
    orm
    -0.12
    res
    -0.12
    iable
    -0.10
    redi
    -0.10
    ings
    -0.10
    r
    -0.10
    rement
    -0.10
    abler
    -0.10
    pedia
    -0.10
    rec
    -0.09
    POSITIVE LOGITS
    quisite
    0.18
    (Core
    0.18
    /Core
    0.17
    ference
    0.17
    -shell
    0.16
    opsis
    0.16
    (core
    0.15
    ographed
    0.14
    lation
    0.14
    ografia
    0.14
    Activations Density 0.021%

    No Known Activations