Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Llama3.3-70B-IT (Instruct)
    3. 50-RESID-POST-GF
    4. 44911
    Prev
    Next
    INDEX
    Explanations

    many problems, her catalog, a fun

    np_acts-logits-general · gemini-2.5-flash-lite

    many

    np_max-act · gemini-2.5-flashTriggered by @aardvarkkr
    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
     Nz
    -0.10
    ãĥĩãĥ«
    -0.09
     Carlton
    -0.09
    itten
    -0.08
    LLU
    -0.08
     oo
    -0.08
     Ment
    -0.08
    ÌĪ
    -0.08
     Flem
    -0.08
    _fixture
    -0.08
    POSITIVE LOGITS
     Claus
    0.12
     sole
    0.11
    ¶Į
    0.10
    ohl
    0.09
    oles
    0.09
    sole
    0.09
     Wright
    0.09
    æ°ı
    0.09
    eto
    0.08
    leigh
    0.08
    Activations Density 0.099%

    No Known Activations