© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 24050
    Prev
    Next
    INDEX
    Explanations

    scents and sounds

    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
     sprink
    -0.10
    381
    -0.09
    .internal
    -0.09
     Helm
    -0.09
     internal
    -0.09
    nofollow
    -0.09
     contain
    -0.09
    lund
    -0.08
    541
    -0.08
     happen
    -0.08
    POSITIVE LOGITS
     wa
    0.22
     hang
    0.14
     hangs
    0.13
    wa
    0.13
     greet
    0.12
     fill
    0.12
     assault
    0.12
     fills
    0.11
     greeted
    0.11
     float
    0.11
    Activations Density 0.067%

    No Known Activations