© 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. 62822
    Prev
    Next
    INDEX
    Explanations

    This is/can

    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
    ewan
    -0.09
    ãĥĸãĥ«
    -0.08
    oad
    -0.08
    agne
    -0.08
    ì¦
    -0.08
     verr
    -0.08
    emouth
    -0.08
    726
    -0.08
    978
    -0.08
    UBLE
    -0.08
    POSITIVE LOGITS
     phenomenon
    0.21
     type
    0.17
     happened
    0.17
     situation
    0.16
     phenomena
    0.15
     could
    0.14
     kind
    0.14
     can
    0.14
     effect
    0.14
     condition
    0.13
    Activations Density 0.042%

    No Known Activations