© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 663
    Prev
    Next
    INDEX
    Explanations

    concerning, existing, remaining, depending

    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
    ffects
    -0.11
    ishments
    -0.10
    agem
    -0.10
    ishment
    -0.10
     Cah
    -0.10
    ake
    -0.09
    imization
    -0.09
    ISM
    -0.09
    pone
    -0.09
    quire
    -0.09
    POSITIVE LOGITS
    ing
    0.34
    izing
    0.30
    çĿĢ
    0.29
    ING
    0.29
    ujÄħ
    0.28
    ating
    0.28
    ujÃŃcÃŃ
    0.27
    ifying
    0.27
    ting
    0.26
    íķĺëĬĶ
    0.25
    Activations Density 0.129%

    No Known Activations