© 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
    3. 50-RESID-POST-GF
    4. 33948
    Prev
    Next
    INDEX
    Explanations

    how questions

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

    questions that ask for an explanation of how something works or functions.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
    .Formatter
    -0.15
    ¶Į
    -0.13
    ÂĢÂĢ
    -0.13
    įng
    -0.13
    ¦æĥħ
    -0.12
    ******č\n
    -0.12
    ¨ë¶Ģ
    -0.12
    EMPLARY
    -0.12
    łéϤ
    -0.11
    ĥ½
    -0.11
    POSITIVE LOGITS
     )\n\n\n\n\n\n\n\n
    0.10
     gig
    0.09
     Hern
    0.09
     machine
    0.08
     Machine
    0.08
    Data
    0.08
     Data
    0.08
     Nun
    0.08
    Machine
    0.07
    ses
    0.07
    Activations Density 0.134%

    No Known Activations