© 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. 61660
    Prev
    Next
    INDEX
    Explanations

    to improve, fix, learn

    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
    wort
    -0.10
    angl
    -0.10
    esch
    -0.09
    zilla
    -0.09
    nob
    -0.09
    stvo
    -0.09
     Dy
    -0.09
    467
    -0.09
    aria
    -0.08
    ｯ
    -0.08
    POSITIVE LOGITS
     familiar
    0.19
     пÑĢивÑĭ
    0.13
    amiliar
    0.13
    çĨŁ
    0.13
     muscle
    0.13
     familiarity
    0.13
    å·
    0.13
     imprint
    0.13
     ìĿµ
    0.12
     build
    0.11
    Activations Density 0.039%

    No Known Activations