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. 65386
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by next utterance

    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
     Geile
    -0.08
    ancel
    -0.08
    .languages
    -0.08
     zbyt
    -0.08
    ィ
    -0.07
    herits
    -0.07
    lass
    -0.07
    askan
    -0.07
    inx
    -0.07
    oku
    -0.07
    POSITIVE LOGITS
    以ä¸Ĭ
    0.12
     hope
    0.10
     END
    0.10
     Note
    0.09
    å¸ĮæľĽ
    0.09
    END
    0.09
    Hope
    0.09
     Hope
    0.09
     note
    0.09
    _END
    0.09
    Activations Density 0.174%

    No Known Activations