© 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
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 12429
    Prev
    Next
    INDEX
    Explanations

    full-year guidance range

    np_acts-logits-general · gemini-2.5-flash-lite

    corporate financial guidance and forecast updates.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @yooniel31
    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
    é¢
    -0.09
    unas
    -0.09
    __/
    -0.09
    ijkstra
    -0.08
     quarterly
    -0.08
    èģĶç½ij
    -0.08
    Äįást
    -0.08
     ilma
    -0.08
    í
    -0.08
     imperfect
    -0.08
    POSITIVE LOGITS
     guidance
    0.21
     range
    0.16
     Guidance
    0.15
     ranges
    0.14
     Range
    0.13
     midpoint
    0.12
     GA
    0.12
     previously
    0.11
     originally
    0.11
    -range
    0.11
    Activations Density 0.034%

    No Known Activations