© 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. 91725
    Prev
    Next
    INDEX
    Explanations

    legal documents

    np_max-act · gemini-2.0-flash

    This neuron detects document metadata lines—especially the labeled page numbers (e.g. “Page 2.355…”) and dates—by picking up the numeric values following “Page:” and “Date” headers.

    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
    Õ
    -0.07
     interrupt
    -0.07
    _tel
    -0.06
     Filipino
    -0.06
    [@"
    -0.06
     uplift
    -0.06
     �
    -0.06
     tl
    -0.06
    InterfaceOrientation
    -0.06
    Tri
    -0.06
    POSITIVE LOGITS
    PHP
    0.08
     وز
    0.07
     прим
    0.07
    siniz
    0.07
    ρηση
    0.07
     σχέ
    0.07
    ').'
    0.06
    reative
    0.06
     mongodb
    0.06
    selectedIndex
    0.06
    Activations Density 0.001%

    No Known Activations