© 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. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 66101
    Prev
    Next
    INDEX
    Explanations

    generally

    np_max-act · gemini-2.0-flash

    The neuron fires on discourse‐level generalization cues—adverbial signals like “more generally,” “more broadly,” or “generally” that introduce a broad summary or general statement.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    technical terms related to material properties and their applications in science.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pie
    -0.07
     ledna
    -0.07
    unittest
    -0.07
     salad
    -0.06
     lái
    -0.06
     xảy
    -0.06
    ipeline
    -0.06
     Orchestra
    -0.06
     示例
    -0.06
    ADOW
    -0.06
    POSITIVE LOGITS
    のような
    0.07
    .getAll
    0.07
    //-----------------------------------------------------------------------------↵
    0.07
    Dem
    0.07
    .addEventListener
    0.07
     regardless
    0.06
    どう
    0.06
    clean
    0.06
     handler
    0.06
    ???↵↵
    0.06
    Activations Density 0.014%

    No Known Activations