© 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. 33969
    Prev
    Next
    INDEX
    Explanations

    anticipating numbered list items

    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
    .scalablytyped
    -0.11
     Atkins
    -0.08
    -hour
    -0.08
    ugo
    -0.08
     Michaels
    -0.08
     tong
    -0.08
    MUX
    -0.08
    union
    -0.08
    翼
    -0.08
    ins
    -0.08
    POSITIVE LOGITS
    EMPLARY
    0.10
    /Dk
    0.10
    ollo
    0.08
    ervo
    0.08
    ften
    0.08
    PageRoute
    0.08
    legg
    0.08
    \Dependency
    0.08
     IDirect
    0.08
     -*-č\n
    0.07
    Activations Density 0.186%

    No Known Activations