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. 65176
    Prev
    Next
    INDEX
    Explanations

    to give a solution

    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
     powdered
    -0.11
     acidic
    -0.10
     Duffy
    -0.09
    quina
    -0.09
     pow
    -0.09
     Moist
    -0.09
     elimination
    -0.08
    èĦĤ
    -0.08
     dame
    -0.08
     condensed
    -0.08
    POSITIVE LOGITS
     solution
    0.37
     solutions
    0.35
     Solution
    0.30
    solution
    0.29
    Solution
    0.29
     Solutions
    0.28
     SOLUTION
    0.26
    _solution
    0.25
    (solution
    0.23
     concentration
    0.22
    Activations Density 0.064%

    No Known Activations