© 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. 44709
    Prev
    Next
    INDEX
    Explanations

    pass away, pass down, pass out

    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
    TickCount
    -0.10
    ial
    -0.09
     Rosenstein
    -0.09
    ction
    -0.09
    ãĥĥãĥĦ
    -0.09
    emachine
    -0.09
    stripe
    -0.09
    lectual
    -0.09
    yles
    -0.08
    uting
    -0.08
    POSITIVE LOGITS
    ively
    0.21
     muster
    0.17
    enger
    0.17
    engers
    0.17
    ag
    0.15
    ivation
    0.15
    ivity
    0.13
     judgment
    0.13
    nger
    0.13
    ivated
    0.12
    Activations Density 0.036%

    No Known Activations