© 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. 1878
    Prev
    Next
    INDEX
    Explanations

    original document

    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
    ĮĴ
    -0.10
    láda
    -0.08
    Mutation
    -0.08
    Å¡ti
    -0.08
     nay
    -0.08
    nave
    -0.08
    datable
    -0.08
    Intialized
    -0.08
    ãĥ£
    -0.08
     FORMAT
    -0.08
    POSITIVE LOGITS
     original
    0.24
    original
    0.18
     originals
    0.18
     Original
    0.15
     document
    0.15
     text
    0.14
    åİŁ
    0.14
     ORIGINAL
    0.14
    .original
    0.14
     passage
    0.13
    Activations Density 0.046%

    No Known Activations