© 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. 56559
    Prev
    Next
    INDEX
    Explanations

    ar ending 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
    y
    -0.16
    ene
    -0.16
    ela
    -0.16
    i
    -0.15
    ens
    -0.14
    ÛĮ
    -0.14
    elle
    -0.14
    a
    -0.13
    am
    -0.13
    د
    -0.13
    POSITIVE LOGITS
    oon
    0.17
    beiten
    0.14
    beiter
    0.14
    rr
    0.14
    oom
    0.13
    ossa
    0.13
    beit
    0.13
    acter
    0.13
    oen
    0.12
    hythm
    0.12
    Activations Density 0.109%

    No Known Activations