© 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. 52021
    Prev
    Next
    INDEX
    Explanations

    rapper identity and roles

    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
    onium
    -0.10
     Yelp
    -0.10
    aoke
    -0.10
    aml
    -0.09
     Helm
    -0.09
     acos
    -0.09
     Emmy
    -0.09
    æ¯Ľ
    -0.09
    ukt
    -0.09
     AC
    -0.09
    POSITIVE LOGITS
     rap
    0.27
    rap
    0.22
     trap
    0.21
     Rap
    0.21
     rapper
    0.19
    rapper
    0.19
     Trap
    0.18
    trap
    0.17
    RAP
    0.15
    Trap
    0.15
    Activations Density 0.090%

    No Known Activations