© 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. 57923
    Prev
    Next
    INDEX
    Explanations

    proposed or specified items

    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
     Hairst
    -0.09
     ais
    -0.09
     znam
    -0.09
    Ðİ
    -0.09
     foregoing
    -0.08
    rschein
    -0.08
    inition
    -0.08
     manifest
    -0.08
    ouce
    -0.08
    Seen
    -0.08
    POSITIVE LOGITS
     proposed
    0.22
     newly
    0.17
     specified
    0.15
     suggested
    0.14
    uggested
    0.14
     previously
    0.13
     reported
    0.13
     given
    0.11
     recommended
    0.11
     Proposed
    0.11
    Activations Density 0.167%

    No Known Activations