© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 13096
    Prev
    Next
    INDEX
    Explanations

    agreement

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of formal partnership or contract signings (e.g. “signed an agreement,” “entered into a deal”).

    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
    _dom
    -0.06
    _album
    -0.06
    	items
    -0.06
    lte
    -0.06
    _scale
    -0.06
    erator
    -0.06
    워
    -0.06
    어
    -0.06
    weise
    -0.06
    barcode
    -0.06
    POSITIVE LOGITS
    取得
    0.06
     frü
    0.06
     Appearance
    0.06
    權
    0.06
     semiclass
    0.06
    LOGIN
    0.06
    Instant
    0.06
    坐在
    0.06
    (box
    0.06
     phá
    0.06
    Activations Density 0.013%

    No Known Activations