© 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
    2. Llama3.3-70B-IT (Instruct)
    3. 50-RESID-POST-GF
    4. 34583
    Prev
    Next
    INDEX
    Explanations

    capable of playing Go

    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
    VR
    -0.09
     Gareth
    -0.09
    Dice
    -0.09
     Bauer
    -0.09
    ring
    -0.09
    ahlen
    -0.09
     Garland
    -0.09
    ooter
    -0.09
     Egg
    -0.09
    rick
    -0.08
    POSITIVE LOGITS
     Alpha
    0.17
     Go
    0.16
     Deep
    0.14
     beat
    0.14
     beating
    0.12
    Alpha
    0.12
     Policy
    0.12
     alph
    0.12
    Go
    0.12
    Deep
    0.11
    Activations Density 0.031%

    No Known Activations