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. 85845
    Prev
    Next
    INDEX
    Explanations

    news articles

    np_max-act · gemini-2.0-flash

    This neuron specializes in detecting publication metadata or citations—mentions of dates, media outlets, “see” pointers, and other reference-style text.

    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
     Symphony
    -0.07
    .linkedin
    -0.07
     sailor
    -0.06
     MediaTek
    -0.06
     Manuals
    -0.06
    λογία
    -0.06
     kennen
    -0.06
     SimpleName
    -0.06
    ゃ
    -0.06
    .accuracy
    -0.06
    POSITIVE LOGITS
     unprotected
    0.07
     Assault
    0.06
    serial
    0.06
     سایر
    0.06
     ipc
    0.06
    icí
    0.06
     civilized
    0.06
    restriction
    0.06
     instructional
    0.06
     pressure
    0.06
    Activations Density 0.041%

    No Known Activations