© 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 (Instruct)
    5. 50-RESID-POST-GF
    7. 44451
    Prev
    Next
    INDEX
    Explanations

    class definitions and related concepts

    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
     Classified
    -0.11
    OfType
    -0.10
     sublist
    -0.10
     categorized
    -0.10
     styl
    -0.10
     inherited
    -0.10
     subgroup
    -0.09
    styl
    -0.09
    arel
    -0.09
     classified
    -0.09
    POSITIVE LOGITS
     class
    0.46
     classes
    0.32
    ç±»
    0.30
    class
    0.29
     classe
    0.27
     íģ´ëŀĺìĬ¤
    0.27
     клаÑģÑģ
    0.26
     clase
    0.25
    \tclass
    0.25
     Class
    0.23
    Activations Density 0.101%

    No Known Activations