© 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. 43390
    Prev
    Next
    INDEX
    Explanations

    "cann" or "ann" related 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
    eren
    -0.13
    er
    -0.12
    ew
    -0.12
    ews
    -0.12
    ey
    -0.11
    erus
    -0.11
    erer
    -0.11
    eyn
    -0.10
    ing
    -0.10
    eward
    -0.10
    POSITIVE LOGITS
    ings
    0.17
    s
    0.16
    ipeg
    0.15
    sylvania
    0.15
    ery
    0.13
    ihilation
    0.13
    ibal
    0.13
    n
    0.12
    ovation
    0.12
    ies
    0.11
    Activations Density 0.051%

    No Known Activations