© 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. 44738
    Prev
    Next
    INDEX
    Explanations

    country names and geography

    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
     tempor
    -0.11
    illo
    -0.10
    ereo
    -0.10
     norm
    -0.10
     bomb
    -0.09
     Norm
    -0.09
    haled
    -0.09
     lecture
    -0.09
    foy
    -0.09
    OUND
    -0.08
    POSITIVE LOGITS
     sector
    0.12
     Arsenal
    0.12
     Gol
    0.11
     arsenal
    0.11
    itespace
    0.10
     cinema
    0.10
    printStats
    0.10
     proletariat
    0.10
     boom
    0.10
    adora
    0.10
    Activations Density 0.129%

    No Known Activations