© 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. 42056
    Prev
    Next
    INDEX
    Explanations

    is attributed

    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
     curled
    -0.10
    AccessType
    -0.09
     Trang
    -0.09
    elts
    -0.09
     prive
    -0.09
     cov
    -0.09
    VertexArray
    -0.08
     Valk
    -0.08
     Verfügung
    -0.08
     ãĢĢ
    -0.08
    POSITIVE LOGITS
     attributed
    0.45
     atrib
    0.43
     attribution
    0.40
     attrib
    0.38
    attrib
    0.38
     attribute
    0.37
    Attrib
    0.35
     Attribution
    0.32
    atrib
    0.31
    attribute
    0.28
    Activations Density 0.173%

    No Known Activations