© 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. 25448
    Prev
    Next
    INDEX
    Explanations

    toolkits, toolchains, tool names

    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
    ustil
    -0.09
    TING
    -0.09
    PostalCodes
    -0.09
    ê¸ī
    -0.09
    eor
    -0.09
    weets
    -0.09
    outers
    -0.09
     NÄĽm
    -0.09
    acus
    -0.09
    odka
    -0.08
    POSITIVE LOGITS
    set
    0.21
    ing
    0.21
    chain
    0.21
    boxes
    0.19
    shed
    0.17
    tips
    0.16
    belt
    0.16
    chest
    0.16
     belt
    0.16
    ç®±
    0.16
    Activations Density 0.030%

    No Known Activations