© 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. 12041
    Prev
    Next
    INDEX
    Explanations

    need any further

    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
    antt
    -0.10
    ulan
    -0.10
    unk
    -0.09
    _ISO
    -0.09
    -urlencoded
    -0.09
    akk
    -0.09
    571
    -0.09
    خاب
    -0.09
    uish
    -0.09
    å¼ĭ
    -0.09
    POSITIVE LOGITS
     anything
    0.33
    anything
    0.24
     Anything
    0.22
    Anything
    0.21
     any
    0.20
     further
    0.19
    ä»»ä½ķ
    0.16
     anymore
    0.15
     changes
    0.14
     changed
    0.14
    Activations Density 0.041%

    No Known Activations