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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Llama3.3-70B-IT (Instruct)
    3. 50-RESID-POST-GF
    4. 44997
    Prev
    Next
    INDEX
    Explanations

    provide helpful information

    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
     Suff
    -0.10
    ãĢĥ
    -0.09
     Wir
    -0.09
     pick
    -0.09
     Reb
    -0.09
    prix
    -0.08
    ToEnd
    -0.08
     Esk
    -0.08
     Sul
    -0.08
    446
    -0.08
    POSITIVE LOGITS
     answer
    0.11
    orno
    0.10
     response
    0.10
     pend
    0.10
    ADO
    0.09
    lea
    0.09
     within
    0.09
    à¹ģà¸ģ
    0.09
    ampa
    0.09
     kepada
    0.09
    Activations Density 0.072%

    No Known Activations