© 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. 44778
    Prev
    Next
    INDEX
    Explanations

    the term or question

    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
    kip
    -0.09
    _utilities
    -0.09
     verbs
    -0.09
     synonyms
    -0.08
    kova
    -0.08
    953
    -0.08
    ochen
    -0.08
    ')."
    -0.08
    FontOfSize
    -0.08
     equipo
    -0.08
    POSITIVE LOGITS
     context
    0.21
     name
    0.17
     person
    0.17
     topic
    0.16
    context
    0.16
     meaning
    0.16
     contexto
    0.15
     subject
    0.15
     Context
    0.15
     reference
    0.15
    Activations Density 0.147%

    No Known Activations