© 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. 44449
    Prev
    Next
    INDEX
    Explanations

    can mean or refer

    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
     Bever
    -0.09
    .mozilla
    -0.09
    aska
    -0.09
     Languages
    -0.09
     Loft
    -0.08
    HIR
    -0.08
     Doming
    -0.08
     Beacon
    -0.08
    ög
    -0.08
    .deepcopy
    -0.08
    POSITIVE LOGITS
     mean
    0.20
     refer
    0.17
    mean
    0.16
     Mean
    0.15
     be
    0.15
    _refer
    0.13
     referring
    0.12
     conn
    0.12
     refers
    0.12
    Mean
    0.11
    Activations Density 0.076%

    No Known Activations