© 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. 38545
    Prev
    Next
    INDEX
    Explanations

    asking questions and requesting answers

    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
    ¶Į
    -0.14
    <|begin_of_text|>
    -0.10
    ¦æĥħ
    -0.09
    ĥ½
    -0.09
    .Dictionary
    -0.09
     CrossAxisAlignment
    -0.09
    otec
    -0.09
    adol
    -0.08
    ÂĢÂĢ
    -0.08
    ıa
    -0.08
    POSITIVE LOGITS
     answer
    0.16
     response
    0.15
     responses
    0.12
     list
    0.12
     information
    0.11
     Answer
    0.11
    answer
    0.11
     enc
    0.10
     reply
    0.10
    Answer
    0.10
    Activations Density 0.912%

    No Known Activations