© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 110754
    Prev
    Next
    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash

    The neuron fires on procedural walkthrough language—especially future‐tense or modal action phrases (e.g. “will appear,” “ask you,” “make sure,” “when he comes”) describing step-by-step game instructions.

    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
     buzzing
    -0.07
     Rah
    -0.07
    _peak
    -0.07
    ADF
    -0.06
    .unique
    -0.06
     Guy
    -0.06
    atinum
    -0.06
     global
    -0.06
    های
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    _CLASSES
    0.07
    appiness
    0.07
     FORE
    0.06
    ################################
    0.06
    ellig
    0.06
     CRM
    0.06
    gallery
    0.06
    setItem
    0.06
    (Op
    0.06
    خر
    0.06
    Activations Density 0.016%

    No Known Activations