© 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. 52430
    Prev
    Next
    INDEX
    Explanations

    general advice and information

    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
    osterone
    -0.10
    ulary
    -0.09
     specific
    -0.09
    ÐŁÐļ
    -0.09
     pid
    -0.09
    licate
    -0.09
    _flip
    -0.09
    stras
    -0.09
    anical
    -0.08
    -hot
    -0.08
    POSITIVE LOGITS
    ised
    0.29
    -purpose
    0.25
    izable
    0.24
    ities
    0.24
    izations
    0.23
    ized
    0.21
    ization
    0.21
    izing
    0.18
    ober
    0.17
    ist
    0.17
    Activations Density 0.022%

    No Known Activations