© 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. 44545
    Prev
    Next
    INDEX
    Explanations

    digital files

    np_max-act · gemini-2.0-flash

    content related to geographical documentation or detailed mapping.

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

    This neuron responds to tokens related to accessing or handling digital files (e.g., download, open, viewable, computer, browser).

    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
    /widgets
    -0.07
     Fruit
    -0.07
    간
    -0.07
    τοκ
    -0.07
    ρες
    -0.07
    衣服
    -0.07
    芙
    -0.07
    _tags
    -0.06
    747
    -0.06
    ière
    -0.06
    POSITIVE LOGITS
    getPath
    0.06
     foresee
    0.06
     protest
    0.06
     }
↵
    0.06
    ?>↵
    0.06
     photographed
    0.06
     sweep
    0.06
    artial
    0.06
    />↵
    0.06
     přítom
    0.06
    Activations Density 0.020%

    No Known Activations