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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Llama3.3-70B-IT (Instruct)
    3. 50-RESID-POST-GF
    4. 65281
    Prev
    Next
    INDEX
    Explanations

    telling and offering information

    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
    ãĤ
    -0.10
    iband
    -0.09
    kees
    -0.09
    /request
    -0.08
    ask
    -0.08
    signals
    -0.08
     REQUEST
    -0.08
    emd
    -0.08
     understanding
    -0.08
     Maiden
    -0.08
    POSITIVE LOGITS
     tell
    0.61
    åijĬè¯ī
    0.54
     tells
    0.52
     telling
    0.50
    tell
    0.46
     told
    0.46
     Tell
    0.45
    Tell
    0.43
     Tells
    0.38
    .tell
    0.37
    Activations Density 0.201%

    No Known Activations