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. 130222
    Prev
    Next
    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash

    The neuron detects patent‐application metadata lines, i.e. the boilerplate “claims priority/benefit of Application No. … filed on …” citations.

    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
     PAD
    -0.08
    Recommend
    -0.07
    .toolStripButton
    -0.06
     consumption
    -0.06
    catalog
    -0.06
    vala
    -0.06
     compatibility
    -0.06
     seamless
    -0.06
    VRT
    -0.06
     MatButtonModule
    -0.06
    POSITIVE LOGITS
    ابع
    0.06
    αρίου
    0.06
     UIEdgeInsets
    0.06
       ↵↵
    0.06
    外
    0.06
     "~
    0.06
    ops
    0.06
    _TXT
    0.06
    .args
    0.06
     -*-↵
    0.06
    Activations Density 0.006%

    No Known Activations