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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 44205
    Prev
    Next
    INDEX
    Explanations

    period followed by word

    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
     either
    -0.10
    ETA
    -0.09
     Baron
    -0.09
     Lust
    -0.09
     optional
    -0.08
    âĢı
    -0.08
     nexus
    -0.08
    usual
    -0.08
    itr
    -0.08
     Valle
    -0.08
    POSITIVE LOGITS
     directly
    0.14
     direct
    0.13
    缴æİ¥
    0.12
    OffsetTable
    0.10
     trá»±c
    0.10
     Ùħباش
    0.10
     ì§ģìłij
    0.10
     ask
    0.10
     непоÑģÑĢед
    0.10
     doÄŁrudan
    0.10
    Activations Density 0.112%

    No Known Activations