© 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. 38106
    Prev
    Next
    INDEX
    Explanations

    sequence-to-sequence approach/pattern/design

    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
     Sherman
    -0.09
    ChangedEventArgs
    -0.09
    ieri
    -0.09
    paralleled
    -0.08
    abbreviation
    -0.08
    usted
    -0.08
    NESS
    -0.08
    /auth
    -0.08
    akte
    -0.08
    earable
    -0.07
    POSITIVE LOGITS
     approach
    0.43
     style
    0.35
     format
    0.33
    -style
    0.32
     Approach
    0.30
    appro
    0.30
    style
    0.26
    å¼ı
    0.24
     structure
    0.22
     manner
    0.21
    Activations Density 0.199%

    No Known Activations