© 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. 44146
    Prev
    Next
    INDEX
    Explanations

    :name

    np_max-act · gemini-2.0-flash

    This neuron fires on Android manifest permission declarations, especially on the android:name attribute in <uses-permission> elements.

    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
    比例
    -0.07
     qi
    -0.06
     Moto
    -0.06
     Ashe
    -0.06
     bets
    -0.06
    =sys
    -0.06
    (df
    -0.06
     вог
    -0.06
     그가
    -0.06
    erview
    -0.06
    POSITIVE LOGITS
     Neuro
    0.07
     Carol
    0.07
     sound
    0.07
    _name
    0.06
    BUS
    0.06
    ematic
    0.06
    verte
    0.06
     documentary
    0.06
    ianne
    0.06
     دام
    0.06
    Activations Density 0.001%

    No Known Activations