Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Llama3.3-70B-IT (Instruct)
    3. 50-RESID-POST-GF
    4. 65465
    Prev
    Next
    INDEX
    Explanations

    names, specific terms, and 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
     himself
    -0.08
    loom
    -0.07
    ıklı
    -0.07
    age
    -0.07
     ï
    -0.07
    d
    -0.07
     âĸł
    -0.07
     stesso
    -0.06
     handsome
    -0.06
     Rom
    -0.06
    POSITIVE LOGITS
    ÂĢÂĢ
    0.11
    įng
    0.10
    .Formatter
    0.10
    <|begin_of_text|>
    0.09
    łéϤ
    0.09
    ******č\n
    0.09
    ¶Į
    0.08
    /epl
    0.08
    .Dictionary
    0.08
    ¦æĥħ
    0.08
    Activations Density 0.220%

    No Known Activations