Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 40632
    Prev
    Next
    INDEX
    Explanations

    artists and writers groups

    np_max-act · gemini-2.0-flash

    The neuron fires on passages listing members of a group or collective, i.e. enumerations of people and their roles in an organization or circle.

    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
     Boston
    -0.07
    .fore
    -0.06
     Manila
    -0.06
    California
    -0.06
    Mir
    -0.06
     Cory
    -0.06
    roc
    -0.06
    _nc
    -0.06
    .mi
    -0.06
    _Project
    -0.06
    POSITIVE LOGITS
     rc
    0.07
    岛
    0.07
    patterns
    0.06
    dataTable
    0.06
    ='".
    0.06
     посл
    0.06
    _CLASSES
    0.06
     vál
    0.06
     odpowied
    0.06
    _dma
    0.06
    Activations Density 0.051%

    No Known Activations