© 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. 43392
    Prev
    Next
    INDEX
    Explanations

    Op

    np_max-act · gemini-2.0-flash

    This neuron recognizes the “Op” token marking the start of a judicial opinion heading (i.e., the “Opinion” label).

    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
    categorie
    -0.07
     preservation
    -0.07
    _don
    -0.07
    udas
    -0.07
     müm
    -0.07
    imum
    -0.06
     περί
    -0.06
    ████
    -0.06
    LESS
    -0.06
    Centre
    -0.06
    POSITIVE LOGITS
     op
    0.14
    OP
    0.12
     Op
    0.12
    Op
    0.12
     OP
    0.11
    -op
    0.11
    	op
    0.10
    op
    0.10
    .Op
    0.10
    _OP
    0.10
    Activations Density 0.015%

    No Known Activations