© 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. 38034
    Prev
    Next
    INDEX
    Explanations

    actions and decisions

    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
     welfare
    -0.10
    Offsets
    -0.09
    utos
    -0.09
    çķ
    -0.08
    isms
    -0.08
    оÑĢоÑĤ
    -0.08
     Ekim
    -0.08
    493
    -0.08
     ï½ľ
    -0.08
    *
    -0.08
    POSITIVE LOGITS
     actions
    0.57
     Actions
    0.44
    actions
    0.43
    Actions
    0.39
    -actions
    0.38
     ACTIONS
    0.37
    _actions
    0.34
     acciones
    0.32
    .actions
    0.32
     decisions
    0.32
    Activations Density 0.123%

    No Known Activations