© 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. 38097
    Prev
    Next
    INDEX
    Explanations

    glad or sorry

    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
     ecstatic
    -0.09
     Rosenberg
    -0.09
     Vita
    -0.09
    ooke
    -0.09
    shield
    -0.09
     trib
    -0.08
    linger
    -0.08
     Hampton
    -0.08
    _mpi
    -0.08
    apiro
    -0.08
    POSITIVE LOGITS
     glad
    0.43
     Glad
    0.35
    lad
    0.19
    gl
    0.16
     pleased
    0.13
     sorry
    0.13
    ple
    0.12
     grateful
    0.11
     grat
    0.11
    Sorry
    0.10
    Activations Density 0.047%

    No Known Activations