© 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. 85693
    Prev
    Next
    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash

    The neuron activates on AndroidManifest XML element names and attributes—especially tags like <activity> or <provider> and their android:name declarations.

    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
    -validator
    -0.07
    strar
    -0.06
    erm
    -0.06
    판
    -0.06
     insistence
    -0.06
    _HINT
    -0.06
     lubric
    -0.06
     pole
    -0.06
     Mich
    -0.06
    ocop
    -0.06
    POSITIVE LOGITS
     Src
    0.06
     Türkiye
    0.06
     returnUrl
    0.06
     декабря
    0.06
    //************************************************************************
    0.06
    slu
    0.06
    :")↵
    0.06
    ています
    0.06
     Bashar
    0.06
     зас
    0.06
    Activations Density 0.002%

    No Known Activations