© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 92497
    Prev
    Next
    INDEX
    Explanations

    article snippets

    np_max-act · gemini-2.0-flash

    information about notable individuals or subjects associated with specific professions or roles.

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

    The neuron activates on descriptions of organizational or project history—especially mentions of founding, construction, funding, and other factual milestones.

    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
     prer
    -0.06
    осуд
    -0.06
    .WriteByte
    -0.06
     ][
    -0.06
     pla
    -0.06
     rh
    -0.06
    -force
    -0.06
    br
    -0.06
    .cat
    -0.06
    Category
    -0.06
    POSITIVE LOGITS
     UIImagePickerController
    0.07
     ред
    0.07
     [~,
    0.06
    IDO
    0.06
     denim
    0.06
     �
    0.06
     Isles
    0.06
     Roose
    0.06
     Oliver
    0.06
     meslek
    0.06
    Activations Density 0.127%

    No Known Activations