© 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. 24193
    Prev
    Next
    INDEX
    Explanations

    examples, lists, etc

    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
    ]
    -0.11
    565
    -0.09
     ï¾Ĭ
    -0.09
     Sic
    -0.08
     Hills
    -0.08
    avig
    -0.08
    /]
    -0.08
     ãĥ¾
    -0.08
    ãĤĬãģ¨
    -0.08
    tuÄŁ
    -0.08
    POSITIVE LOGITS
     etc
    0.29
    etc
    0.22
     ÑĤоÑīо
    0.15
    ãģªãģ©
    0.15
     ëĵ±
    0.13
    çŃī
    0.13
    /etc
    0.13
     vs
    0.13
     atd
    0.12
     çŃī
    0.10
    Activations Density 0.167%

    No Known Activations