© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 89691
    Prev
    Next
    INDEX
    Explanations

    avi

    np_max-act · gemini-2.0-flash

    the neuron detects mentions of consumer items or commercial/monetary goods.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    references to special events or significant celebrations.

    oai_token-act-pair · gpt-4o-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
    uncio
    -0.06
     demande
    -0.06
    页面存档备份
    -0.06
     đài
    -0.06
     standart
    -0.06
     Hải
    -0.06
     ConsoleColor
    -0.06
     Guild
    -0.06
     squadron
    -0.06
     ο
    -0.05
    POSITIVE LOGITS
    respect
    0.08
     مج
    0.07
    lerin
    0.07
     deterrent
    0.07
    .TR
    0.07
    ech
    0.06
     tecn
    0.06
     *</
    0.06
     prerequisite
    0.06
    ضع
    0.06
    Activations Density 0.345%

    No Known Activations