© 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. 61628
    Prev
    Next
    INDEX
    Explanations

    providing examples or details

    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
    å®ĥ
    -0.11
     ambos
    -0.10
     beide
    -0.10
     BOTH
    -0.09
    两人
    -0.09
     its
    -0.09
    612
    -0.09
    hei
    -0.09
     Both
    -0.09
     followed
    -0.08
    POSITIVE LOGITS
    å®ĥ们
    0.24
     each
    0.21
     ones
    0.19
     Each
    0.18
     these
    0.18
    è¿ĻäºĽ
    0.18
     them
    0.18
     à¤ĩनà¤ķ
    0.18
    "These
    0.17
    each
    0.17
    Activations Density 0.233%

    No Known Activations