© 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. 38170
    Prev
    Next
    INDEX
    Explanations

    Je suisSorry

    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
    chan
    -0.09
     fug
    -0.09
     chẳng
    -0.09
     inaug
    -0.09
    expr
    -0.09
     se
    -0.09
    wel
    -0.08
     longitud
    -0.08
    prene
    -0.08
    ul
    -0.08
    POSITIVE LOGITS
     here
    0.15
     sorry
    0.12
     glad
    0.11
     Sorry
    0.11
    Sorry
    0.11
     aquÃŃ
    0.10
    sorry
    0.10
    ãģĵãģĵ
    0.10
     myself
    0.10
     здеÑģÑĮ
    0.10
    Activations Density 0.089%

    No Known Activations