© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 38725
    Prev
    Next
    INDEX
    Explanations

    gathering documents

    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
    Approved
    -0.09
    ppt
    -0.09
     Approved
    -0.08
     recording
    -0.08
    ynom
    -0.08
    printer
    -0.08
    _ENTRY
    -0.08
    ract
    -0.08
     jeopardy
    -0.08
     refunds
    -0.08
    POSITIVE LOGITS
     documents
    0.33
     supporting
    0.29
     documentation
    0.26
     Documents
    0.25
    documents
    0.25
     Supporting
    0.24
     documentos
    0.23
    Documents
    0.22
    _documents
    0.21
     docs
    0.20
    Activations Density 0.081%

    No Known Activations