© 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. 55421
    Prev
    Next
    INDEX
    Explanations

    android

    np_max-act · gemini-2.0-flash

    This neuron fires on XML element names belonging to Android’s support‐library widget packages (e.g. tags like android.support.v4.widget.DrawerLayout or android.support.design.widget.CoordinatorLayout).

    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
    .getBody
    -0.06
    _spacing
    -0.06
    ácil
    -0.06
    ackle
    -0.06
     Rog
    -0.06
    .ld
    -0.06
     Submission
    -0.06
     metav
    -0.06
     Rak
    -0.06
    .front
    -0.06
    POSITIVE LOGITS
    XM
    0.07
     propelled
    0.07
    ури
    0.06
     친
    0.06
    anoia
    0.06
     quint
    0.06
     glamorous
    0.06
    nea
    0.06
     ToDo
    0.06
    �
    0.06
    Activations Density 0.014%

    No Known Activations