© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 68518
    Prev
    Next
    INDEX
    Explanations

    people and businesses

    np_max-act · gemini-2.0-flash

    the definition and relevant information about pharmaceutical companies, specifically focusing on their operations and impact in the chemical industry.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron activates on mentions of local people or persons (e.g. “local person,” “local people”).

    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
     realms
    -0.06
     tail
    -0.06
    098
    -0.06
     Frankie
    -0.06
    ’all
    -0.05
    pol
    -0.05
    ])*
    -0.05
    _numbers
    -0.05
    Holiday
    -0.05
    *z
    -0.05
    POSITIVE LOGITS
    ॉफ
    0.07
    getContext
    0.06
    醫
    0.06
    powered
    0.06
    _outline
    0.06
    (tasks
    0.06
    }/#{
    0.06
     Defines
    0.06
    fadeOut
    0.06
    	margin
    0.06
    Activations Density 0.040%

    No Known Activations