© 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. 38093
    Prev
    Next
    INDEX
    Explanations

    only considers past

    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
     wed
    -0.09
     PREF
    -0.09
     Palace
    -0.09
     Ded
    -0.09
     Dart
    -0.09
     Qed
    -0.09
     Projection
    -0.08
     Pref
    -0.08
    sf
    -0.08
     Fah
    -0.08
    POSITIVE LOGITS
     context
    0.16
     feedback
    0.15
     past
    0.15
     previous
    0.14
    context
    0.13
     fed
    0.13
    feedback
    0.13
     history
    0.13
     decisions
    0.13
    _feedback
    0.12
    Activations Density 0.110%

    No Known Activations