© 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
    5. 50-RESID-POST-GF
    7. 33909
    Prev
    Next
    INDEX
    Explanations

    between entities or relationships

    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
    ngo
    -0.08
    zia
    -0.08
    ög
    -0.08
     Bylo
    -0.08
    ;;;;;;;;;;;;;;;;
    -0.08
    932
    -0.08
    IFn
    -0.08
     Clo
    -0.08
     adj
    -0.08
    ³
    -0.08
    POSITIVE LOGITS
     between
    0.81
     giữa
    0.61
    between
    0.61
     Between
    0.60
     междÑĥ
    0.60
     zwischen
    0.58
     tussen
    0.55
    Between
    0.54
     BETWEEN
    0.53
     mezi
    0.49
    Activations Density 0.248%

    No Known Activations