© 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
    5. 50-RESID-POST-GF
    7. 44287
    Prev
    Next
    INDEX
    Explanations

    postcard or card

    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
    稿
    -0.10
    åħ¥ãĤĬ
    -0.09
    anter
    -0.08
     Signature
    -0.08
    avad
    -0.08
    окон
    -0.08
    ubic
    -0.08
    esz
    -0.08
    ListItemIcon
    -0.08
     Nico
    -0.08
    POSITIVE LOGITS
     card
    0.64
     cards
    0.54
     Card
    0.48
    card
    0.45
     Cards
    0.42
    Card
    0.41
    -card
    0.40
    cards
    0.38
    .card
    0.38
    (card
    0.37
    Activations Density 0.054%

    No Known Activations