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. 45013
    Prev
    Next
    INDEX
    Explanations

    moving on and accepting

    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
     resc
    -0.12
     reconc
    -0.10
    hir
    -0.09
     Nir
    -0.09
     runoff
    -0.09
     corre
    -0.09
     Dropout
    -0.09
     lag
    -0.09
     Retirement
    -0.09
     rescue
    -0.09
    POSITIVE LOGITS
     healing
    0.20
     Healing
    0.17
     heal
    0.15
     heals
    0.14
     healed
    0.14
     moving
    0.13
    Closure
    0.13
     num
    0.13
     slowly
    0.13
     numb
    0.13
    Activations Density 0.055%

    No Known Activations