© 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. 34518
    Prev
    Next
    INDEX
    Explanations

    expressions of desire or ability

    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
    ï¼ıï¼ı
    -0.10
     Grain
    -0.10
    oir
    -0.10
    requete
    -0.09
    olina
    -0.09
    asil
    -0.09
    636
    -0.09
    _RPC
    -0.09
    auer
    -0.08
    827
    -0.08
    POSITIVE LOGITS
     want
    0.25
     wouldn
    0.24
     wants
    0.23
     muá»ijn
    0.21
    want
    0.20
    Want
    0.19
     Want
    0.18
     wanting
    0.18
     quiero
    0.17
     unwilling
    0.17
    Activations Density 0.065%

    No Known Activations