© 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. 34546
    Prev
    Next
    INDEX
    Explanations

    suspect arrested on

    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
    ĮĴ
    -0.13
    ıa
    -0.12
    ÂĢÂĢ
    -0.11
    ¶Į
    -0.11
     -*-č\n
    -0.11
    ¦æĥħ
    -0.10
    .synthetic
    -0.10
    EMPLARY
    -0.10
    DCALL
    -0.09
    ******č\n
    -0.09
    POSITIVE LOGITS
     *
    0.11
     cas
    0.09
     recently
    0.09
     **
    0.09
     mau
    0.09
     last
    0.09
     Mali
    0.09
     ,
    0.08
    isa
    0.08
    ,
    0.08
    Activations Density 0.037%

    No Known Activations