© 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. 31925
    Prev
    Next
    INDEX
    Explanations

    iv logic and rivais

    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
    al
    -0.18
    alist
    -0.14
    es
    -0.14
    alg
    -0.14
    Ø©
    -0.13
    ali
    -0.13
    alis
    -0.13
    alion
    -0.12
    alie
    -0.12
    alc
    -0.12
    POSITIVE LOGITS
    s
    0.26
    à¥įह
    0.14
    erson
    0.13
    ÑĪиÑģÑĮ
    0.13
    olution
    0.13
    raison
    0.12
    ileged
    0.11
    est
    0.11
    orous
    0.10
    vy
    0.10
    Activations Density 0.056%

    No Known Activations