© 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. 13456
    Prev
    Next
    INDEX
    Explanations

    conversational

    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
    erv
    -0.11
    .MixedReality
    -0.11
    ertools
    -0.10
    utes
    -0.10
    umbling
    -0.09
    OLEAN
    -0.09
    ounding
    -0.09
    มาร
    -0.09
     ass
    -0.08
    uania
    -0.08
    POSITIVE LOGITS
    ational
    0.18
    ión
    0.16
    ations
    0.15
    ely
    0.14
     convers
    0.13
    ing
    0.13
    atile
    0.13
    ative
    0.12
    ga
    0.12
    azione
    0.12
    Activations Density 0.019%

    No Known Activations