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

    Neuronpedia

    Jacobian LensNEW
    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. 56994
    Prev
    Next
    INDEX
    Explanations

    App

    np_max-act · gemini-2.0-flash

    The neuron fires on the case‐heading role labels “Appellant” and “Appellee” (i.e. party designations in legal briefs).

    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
     Compatible
    -0.07
     INIT
    -0.06
     fingert
    -0.06
    KeySpec
    -0.06
    encoder
    -0.06
     ListTile
    -0.06
    .Prot
    -0.06
    -neck
    -0.06
     가능
    -0.06
     productName
    -0.06
    POSITIVE LOGITS
    Queue
    0.06
     Sever
    0.06
     Shots
    0.06
    (cell
    0.06
    Bo
    0.06
     Vo
    0.06
     dạy
    0.06
    注册
    0.06
    ])]
    0.06
    light
    0.06
    Activations Density 0.003%

    No Known Activations