© 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. 89872
    Prev
    Next
    INDEX
    Explanations

    requesting information

    np_max-act · gemini-2.0-flash

    This neuron detects polite, imperative requests asking readers to report errors or violations (e.g. “please inform us,” “please notify,” “if you find any inaccuracies”).

    oai_token-act-pair · o4-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
    なの
    -0.07
    imin
    -0.06
     hoá
    -0.06
     devote
    -0.06
    /display
    -0.06
     jede
    -0.06
     ngôn
    -0.06
    инов
    -0.06
     lan
    -0.06
     browsing
    -0.06
    POSITIVE LOGITS
     Garcia
    0.07
    Reaction
    0.07
    phetamine
    0.07
    ización
    0.06
    alış
    0.06
    Birth
    0.06
    Styles
    0.06
     advertised
    0.06
    erdings
    0.06
     diversified
    0.06
    Activations Density 0.012%

    No Known Activations