© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 54088
    Prev
    Next
    INDEX
    Explanations

    offer

    np_max-act · gemini-2.0-flash

    This neuron detects the appearance of the word “offer” in a formal/legal correspondence context.

    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
     Clayton
    -0.07
    brane
    -0.07
    جان
    -0.06
     cell
    -0.06
     Chap
    -0.06
     JC
    -0.06
    Page
    -0.06
    ием
    -0.06
    _ajax
    -0.06
    cházet
    -0.06
    POSITIVE LOGITS
     offer
    0.09
     Offer
    0.08
     Οικο
    0.07
    offer
    0.07
    ΟΡ
    0.07
    .ver
    0.07
     تشکیل
    0.07
    iffe
    0.07
     merchandise
    0.07
     mails
    0.07
    Activations Density 0.008%

    No Known Activations