© 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. 34686
    Prev
    Next
    INDEX
    Explanations

    questions about legal or factual situations

    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
     Sort
    -0.10
     Vor
    -0.09
    ège
    -0.08
    ÃĹ\n\n
    -0.08
    EMPLARY
    -0.08
    uters
    -0.08
    ãĢĢï½Į
    -0.08
    /******/
    -0.08
    appen
    -0.08
    alg
    -0.08
    POSITIVE LOGITS
    Which
    0.13
     Which
    0.13
     question
    0.12
     How
    0.12
     Question
    0.11
    .scalablytyped
    0.11
     What
    0.11
     how
    0.11
     do
    0.10
    æģ
    0.09
    Activations Density 0.228%

    No Known Activations