© 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. 19929
    Prev
    Next
    INDEX
    Explanations

    assistant<|end_header_id|>\n\n

    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
    inati
    -0.10
    ä¸ĩ
    -0.10
    ati
    -0.09
     Remember
    -0.09
     Pant
    -0.08
    chos
    -0.08
    uh
    -0.08
    yne
    -0.08
    ours
    -0.08
    enth
    -0.08
    POSITIVE LOGITS
     sounds
    0.19
    sounds
    0.17
    Sounds
    0.17
     Sounds
    0.16
     what
    0.13
    what
    0.11
     understood
    0.11
    çIJĨ解
    0.11
     interess
    0.10
    ä½ł
    0.10
    Activations Density 0.329%

    No Known Activations