© 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. 44250
    Prev
    Next
    INDEX
    Explanations

    quotes

    np_max-act · gemini-2.0-flash

    This neuron detects JSON object property definitions—specifically a quoted key followed immediately by the colon separator before its value.

    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
     brink
    -0.07
     JSImport
    -0.07
    ЙЙ
    -0.07
     needy
    -0.07
    pl
    -0.07
    loor
    -0.07
    vekili
    -0.06
     iken
    -0.06
     mysteries
    -0.06
    _feed
    -0.06
    POSITIVE LOGITS
    _VALIDATE
    0.07
    ål
    0.07
     Brisbane
    0.06
     '\'
    0.06
    _]
    0.06
     Measurements
    0.06
     Karachi
    0.06
     Railroad
    0.06
    0.06
    :>
    0.06
    Activations Density 0.017%

    No Known Activations