© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 56679
    Prev
    Next
    INDEX
    Explanations

    HY

    np_max-act · gemini-2.0-flash

    This neuron detects occurrences of the “Developer NAME_1” developer-mode prompt tokens (i.e. the special Developer_NAME_1 tag).

    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
     сад
    -0.06
    یین
    -0.06
    ์ค
    -0.06
    ode
    -0.06
    kol
    -0.06
    _TH
    -0.06
    ์ล
    -0.06
    verte
    -0.06
     있었
    -0.06
    _ENT
    -0.06
    POSITIVE LOGITS
     ],↵
    0.08
    .tip
    0.06
    .getStyle
    0.06
     TextStyle
    0.06
     工
    0.06
     createStore
    0.06
     battles
    0.06
    の一
    0.06
     họa
    0.06
     processor
    0.06
    Activations Density 0.003%

    No Known Activations