© 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. 34105
    Prev
    Next
    INDEX
    Explanations

    concept + specific term

    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
     situations
    -0.11
     kinds
    -0.09
    pts
    -0.09
     ÑĦÑĥнда
    -0.09
    Nib
    -0.08
    []={
    -0.08
    crets
    -0.08
     types
    -0.08
    _epsilon
    -0.08
     Corps
    -0.08
    POSITIVE LOGITS
     itself
    0.20
     aspect
    0.16
     portion
    0.15
     aspects
    0.13
    iest
    0.12
     medium
    0.11
     gods
    0.11
     process
    0.10
    portion
    0.10
     portions
    0.10
    Activations Density 0.172%

    No Known Activations