© 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. 61938
    Prev
    Next
    INDEX
    Explanations

    hip-hop, hip-hop, hypothetical, hip-hop

    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
    ìķ¼
    -0.10
    loha
    -0.10
    bare
    -0.09
    lin
    -0.09
    ousel
    -0.09
    ล
    -0.09
    arily
    -0.09
    OUS
    -0.09
    lined
    -0.09
    VK
    -0.09
    POSITIVE LOGITS
    -hop
    0.21
    ster
    0.19
     hop
    0.17
    sters
    0.17
     Hop
    0.15
    per
    0.14
    pos
    0.14
    Hop
    0.13
    ocrisy
    0.12
    ocrates
    0.11
    Activations Density 0.017%

    No Known Activations