© 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
    2. Llama3.3-70B-IT
    3. 50-RESID-POST-GF
    4. 39801
    Prev
    Next
    INDEX
    Explanations

    end of clause punctuation

    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
    __":\n
    -0.13
    EMPLARY
    -0.11
     Hin
    -0.10
    ":\n\n
    -0.09
    ":\n
    -0.09
    ystate
    -0.09
    ÐIJÑĢÑħÑĸв
    -0.09
     })).
    -0.08
    ':\n\n
    -0.08
    __':\n
    -0.08
    POSITIVE LOGITS
    ).\n
    0.09
    >.\n
    0.08
    );\n
    0.08
    ){}\n
    0.08
    '.\n
    0.08
    ?
    0.08
    }})\n
    0.08
     ![
    0.08
    ãĢĤ\n
    0.08
     Bast
    0.08
    Activations Density 0.082%

    No Known Activations