© 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. 29689
    Prev
    Next
    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash

    The neuron fires on tokens used in document section headings and structural markup (e.g. “sec”, “#”, colons, “background”, “appendix”, etc.), i.e. it detects section‐header metadata.

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

    concepts related to data-driven modeling and control in energy systems.

    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
     захисту
    -0.07
    했습니다
    -0.07
    _EXPR
    -0.07
     umožňuje
    -0.07
    ืน
    -0.06
    列表
    -0.06
    WebService
    -0.06
    .pro
    -0.06
    ading
    -0.06
    移動
    -0.06
    POSITIVE LOGITS
     Dies
    0.07
     infect
    0.07
    	active
    0.07
     basement
    0.06
    ioxid
    0.06
     datasets
    0.06
    лено
    0.06
     INTER
    0.06
     Liverpool
    0.06
     daytime
    0.06
    Activations Density 0.001%

    No Known Activations