© 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. 54131
    Prev
    Next
    INDEX
    Explanations

    file names and proper nouns

    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
     unspecified
    -0.09
    ##_
    -0.08
    ]âĢı
    -0.08
    ettings
    -0.08
     seins
    -0.08
    643
    -0.07
     Edmund
    -0.07
    lest
    -0.07
    emo
    -0.07
    orton
    -0.07
    POSITIVE LOGITS
    ฯ
    0.26
     Králové
    0.10
     Pradesh
    0.09
    æ°ı
    0.09
    _Tis
    0.08
    andez
    0.08
    -animate
    0.08
    าà¸
    0.08
    çĴĥ
    0.08
    ĥĿ
    0.08
    Activations Density 0.165%

    No Known Activations