© 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. 38541
    Prev
    Next
    INDEX
    Explanations

    introductions and code contexts

    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
     skl
    -0.08
    oda
    -0.08
     [+
    -0.07
    ymm
    -0.07
    wins
    -0.07
     particul
    -0.07
    jud
    -0.07
     poor
    -0.07
    uru
    -0.07
     JpaRepository
    -0.07
    POSITIVE LOGITS
    utut
    0.09
    azzo
    0.08
    braco
    0.08
    ült
    0.08
    _Lean
    0.07
    <decltype
    0.07
    .asInstanceOf
    0.07
    :maj
    0.07
    ¼
    0.07
     overload
    0.07
    Activations Density 0.146%

    No Known Activations