© 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. 6774
    Prev
    Next
    INDEX
    Explanations

    studied

    np_max-act · gemini-2.0-flash

    The neuron detects passive‐perfect scientific phrasing—especially “have/been … studied” often modified by adverbs like “extensively,” “widely,” or “comprehensively.”

    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
    uç
    -0.09
    ün
    -0.07
     Mayıs
    -0.07
    -yellow
    -0.07
    士
    -0.07
    \Block
    -0.06
     کیل
    -0.06
    uw
    -0.06
     Seç
    -0.06
    .histogram
    -0.06
    POSITIVE LOGITS
    351
    0.07
    pcodes
    0.06
     Rockets
    0.06
     přip
    0.06
    .weapon
    0.06
    "%(
    0.06
    计算
    0.06
    &D
    0.06
    算
    0.06
     predis
    0.06
    Activations Density 0.040%

    No Known Activations