Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 91055
    Prev
    Next
    INDEX
    Explanations

    :name

    np_max-act · gemini-2.0-flash

    XML tags and attributes related to Android application manifests.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron detects XML intent‐filter category entries for the Android “LAUNCHER” action.

    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
    Chi
    -0.07
    StartupScript
    -0.07
    Cancelar
    -0.06
     Senior
    -0.06
    ências
    -0.06
     Underground
    -0.06
     letto
    -0.06
     Warcraft
    -0.06
    _scale
    -0.06
     ensuite
    -0.06
    POSITIVE LOGITS
     /************************************************************************
    0.07
    机关
    0.06
    -save
    0.06
    )^
    0.06
     대한
    0.06
     ['./
    0.06
     lä
    0.06
     є
    0.06
     Width
    0.06
    _esc
    0.06
    Activations Density 0.000%

    No Known Activations