© 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
    2. Llama3.3-70B-IT
    3. 50-RESID-POST-GF
    4. 2521
    Prev
    Next
    INDEX
    Explanations

    items or concepts followed by details

    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
    (s
    -0.14
     itself
    -0.14
    that
    -0.12
    ooth
    -0.11
    oft
    -0.10
    ynchronize
    -0.10
    abet
    -0.10
    ingleton
    -0.10
    of
    -0.10
    to
    -0.10
    POSITIVE LOGITS
     themselves
    0.17
    ’;
    0.15
    heets
    0.15
    cape
    0.14
     thems
    0.14
    heet
    0.13
    '
    0.13
     weren
    0.12
     were
    0.12
    ight
    0.10
    Activations Density 0.289%

    No Known Activations