© 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. 34741
    Prev
    Next
    INDEX
    Explanations

    conditional or required phrasing

    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
     if
    -0.11
    ija
    -0.10
     pokud
    -0.09
    hazi
    -0.09
     Hamp
    -0.09
     Hatch
    -0.09
    oman
    -0.09
     IEntity
    -0.08
    oci
    -0.08
    IfNeeded
    -0.08
    POSITIVE LOGITS
    çļĦè¯Ŀ
    0.18
    /app
    0.16
    /if
    0.14
    /request
    0.12
     конеÑĩно
    0.10
    /App
    0.09
    izz
    0.09
     otherwise
    0.09
    /as
    0.09
     Griffith
    0.09
    Activations Density 0.067%

    No Known Activations