© 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
    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. 43427
    Prev
    Next
    INDEX
    Explanations

    movie and album releases

    np_max-act · gemini-2.0-flash

    The neuron fires on words and phrases signaling the announcement or release of new media (e.g. albums, movies, etc.).

    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
    _bh
    -0.07
    cba
    -0.07
    locations
    -0.06
    وح
    -0.06
    (currency
    -0.06
    559
    -0.06
     bre
    -0.06
    566
    -0.06
     swamp
    -0.06
    (val
    -0.06
    POSITIVE LOGITS
    컴
    0.07
     Persons
    0.07
     nouvelles
    0.06
    .sendRedirect
    0.06
    例
    0.06
     inmate
    0.06
     thảo
    0.06
     çağ
    0.06
    _EXIST
    0.06
    .scalar
    0.06
    Activations Density 0.025%

    No Known Activations