© 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. 44259
    Prev
    Next
    INDEX
    Explanations

    several steps to solutions

    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
     Decision
    -0.10
    ollo
    -0.09
    ãĤ´ãĥª
    -0.09
     Pole
    -0.09
    Decision
    -0.09
    sett
    -0.09
     rencont
    -0.09
     regimes
    -0.08
     caffe
    -0.08
     salv
    -0.08
    POSITIVE LOGITS
     solutions
    0.24
     Solutions
    0.20
     solution
    0.19
     Lös
    0.16
     SOLUTION
    0.15
     approach
    0.14
     address
    0.14
     action
    0.14
     approaches
    0.14
    _solution
    0.13
    Activations Density 0.132%

    No Known Activations