© 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. 29311
    Prev
    Next
    INDEX
    Explanations

    It is with a heavy heart

    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
    Thunk
    -0.10
     based
    -0.09
     original
    -0.09
     cool
    -0.09
     ann
    -0.09
    éħ
    -0.09
    oure
    -0.09
     help
    -0.09
     Original
    -0.09
     love
    -0.08
    POSITIVE LOGITS
    euillez
    0.12
     kÃŃnh
    0.10
    allow
    0.10
    .ordinal
    0.10
     cord
    0.09
     Allow
    0.09
    hread
    0.09
    endid
    0.09
     Mess
    0.09
    loquent
    0.09
    Activations Density 0.128%

    No Known Activations