© 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. 56101
    Prev
    Next
    INDEX
    Explanations

    но / важно

    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
    du
    -0.11
    medi
    -0.11
    ler
    -0.11
    ro
    -0.11
    com
    -0.11
    ment
    -0.11
    ning
    -0.11
    man
    -0.10
    gen
    -0.10
    bling
    -0.10
    POSITIVE LOGITS
    ÅĽÄĩ
    0.16
    еÐ
    0.14
    Ñģлов
    0.11
    /epl
    0.11
    edata
    0.11
    Ñħод
    0.10
    ÑĨен
    0.10
    ’;nun
    0.10
    Ñĩного
    0.10
    Ñıз
    0.10
    Activations Density 0.076%

    No Known Activations