© 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. 125084
    Prev
    Next
    INDEX
    Explanations

    abundance

    np_max-act · gemini-2.0-flash

    This neuron responds to quantitative scientific measurements, particularly element abundance values and their associated terminology.

    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
     весь
    -0.06
     кус
    -0.06
    忙
    -0.06
    闭
    -0.06
     таким
    -0.06
    ματο
    -0.05
     อำเภ
    -0.05
     mensajes
    -0.05
    amiento
    -0.05
    /validation
    -0.05
    POSITIVE LOGITS
     topLevel
    0.07
    رة
    0.07
     Tobacco
    0.07
     List
    0.07
     ساز
    0.06
    "%(
    0.06
    _MEMBER
    0.06
     vừa
    0.06
    秀
    0.06
    .preference
    0.06
    Activations Density 0.003%

    No Known Activations