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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 68330
    Prev
    Next
    INDEX
    Explanations

    store

    np_max-act · gemini-2.0-flash

    comparative discussions about mobile operating systems.

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

    This neuron responds to mentions of mobile app distribution platforms (e.g. “App Store,” “Google Play Store”).

    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
    ASHINGTON
    -0.07
    .Dom
    -0.07
     observable
    -0.06
    iotics
    -0.06
    -paper
    -0.06
    refix
    -0.06
     cars
    -0.06
    (tags
    -0.06
    CUS
    -0.06
    قم
    -0.06
    POSITIVE LOGITS
     baz
    0.07
     revisit
    0.06
     мист
    0.06
     butt
    0.06
     ваш
    0.06
    STORE
    0.06
    าการ
    0.06
     altern
    0.06
    -ie
    0.06
     mischief
    0.06
    Activations Density 0.009%

    No Known Activations