© 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 (Instruct)
    3. 50-RESID-POST-GF
    4. 38012
    Prev
    Next
    INDEX
    Explanations

    when followed by NAME_2

    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
     hath
    -0.09
    pollo
    -0.09
    emic
    -0.09
    ži
    -0.09
    sted
    -0.09
    pit
    -0.08
    StateManager
    -0.08
     ÐĴоÑĤ
    -0.08
    startswith
    -0.08
    าà¸ĺ
    -0.08
    POSITIVE LOGITS
     till
    0.10
     fare
    0.09
     Opport
    0.09
     til
    0.09
     shall
    0.09
     ëĺIJ
    0.09
     Jud
    0.09
    fair
    0.09
     piping
    0.09
     perhaps
    0.09
    Activations Density 0.081%

    No Known Activations