© 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. 28266
    Prev
    Next
    INDEX
    Explanations

    concerns about life situations

    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
    ijken
    -0.09
    iate
    -0.09
    ardi
    -0.09
     ê²
    -0.09
    /we
    -0.09
    614
    -0.09
     Proud
    -0.08
     اÙĦرÙħزÙĬØ©
    -0.08
    æĺ¯æĪij
    -0.08
    ancellor
    -0.08
    POSITIVE LOGITS
     hãy
    0.19
     thì
    0.17
    ï¼Į请
    0.16
     maka
    0.16
    çļĦè¯Ŀ
    0.15
     please
    0.15
     consider
    0.13
    please
    0.13
     try
    0.12
    ï¼ĮåĪĻ
    0.12
    Activations Density 0.075%

    No Known Activations