© 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. 44321
    Prev
    Next
    INDEX
    Explanations

    .com and .org addresses

    np_max-act · gemini-2.0-flash

    The neuron activates on URL fragments—especially domain and top‐level‐domain tokens like “.com,” “.org,” and similar link bits.

    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
    -src
    -0.07
     Mention
    -0.07
    -eff
    -0.07
     بزرگ
    -0.06
    -tag
    -0.06
     یافته
    -0.06
     wij
    -0.06
    주시
    -0.06
    .inter
    -0.06
    _EFFECT
    -0.06
    POSITIVE LOGITS
     Philippine
    0.06
    사의
    0.06
    么
    0.06
     fiscal
    0.06
    inputs
    0.06
     ateş
    0.06
    _primitive
    0.06
     организа
    0.06
     Polyester
    0.06
     захворювання
    0.06
    Activations Density 0.005%

    No Known Activations