© 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. 7959
    Prev
    Next
    INDEX
    Explanations

    JSON security data

    np_max-act · gemini-2.0-flash

    This neuron detects occurrences of a JSON "action" field (i.e. the key "action" and its associated structure).

    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
    谓
    -0.07
    лекс
    -0.07
    pb
    -0.07
     Bild
    -0.06
    getRoot
    -0.06
    \.
    -0.06
     Congressional
    -0.06
     nett
    -0.06
    small
    -0.06
     RAD
    -0.06
    POSITIVE LOGITS
     groundwork
    0.07
     intéress
    0.06
    THR
    0.06
     wheels
    0.06
     regexp
    0.06
    ?,
    0.05
    扎
    0.05
     backstory
    0.05
     traditions
    0.05
    ，本
    0.05
    Activations Density 0.006%

    No Known Activations