© 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. 59202
    Prev
    Next
    INDEX
    Explanations

    note followed by colon or that

    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
    cw
    -0.09
    ëĭ¹
    -0.09
    apse
    -0.09
    s
    -0.09
    ref
    -0.09
    ouve
    -0.09
    d
    -0.09
    propri
    -0.09
    igor
    -0.08
     candid
    -0.08
    POSITIVE LOGITS
     bene
    0.12
     rằng
    0.12
    .Note
    0.12
    -taking
    0.12
    books
    0.11
    boom
    0.11
     bahwa
    0.11
    ably
    0.10
    :
    0.10
    boo
    0.10
    Activations Density 0.014%

    No Known Activations