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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 130581
    Prev
    Next
    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash

    The neuron detects bibliographic metadata phrases indicating where and when a study is published (e.g. “appears in the … issue of the journal”).

    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
    Md
    -0.06
    ienne
    -0.06
    ink
    -0.06
     شود
    -0.06
     rehabilit
    -0.06
    _emp
    -0.06
     plugin
    -0.06
     Laboratory
    -0.06
     Device
    -0.06
    ştir
    -0.06
    POSITIVE LOGITS
    -document
    0.06
    ombres
    0.06
     caches
    0.06
     dışında
    0.06
     asıl
    0.06
     advertisers
    0.06
     lij
    0.06
     imagery
    0.06
     sürede
    0.06
    �
    0.06
    Activations Density 0.009%

    No Known Activations