© 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. 41466
    Prev
    Next
    INDEX
    Explanations

    different people different perspectives

    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
     Berger
    -0.09
     distinctions
    -0.09
    arily
    -0.09
    âĹıâĹı
    -0.09
    ABCDEFGHIJKLMNOP
    -0.09
    ABCDEFG
    -0.09
     Warp
    -0.08
    ãĤ¼
    -0.08
    avar
    -0.08
     Victim
    -0.08
    POSITIVE LOGITS
     interpret
    0.13
    interpret
    0.12
     Interpret
    0.11
     withd
    0.11
    æ®Ĭ
    0.11
     cherry
    0.10
     interpre
    0.10
    interpreted
    0.10
    ifferent
    0.10
     interpretation
    0.10
    Activations Density 0.033%

    No Known Activations