© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 41083
    Prev
    Next
    INDEX
    Explanations

    databases and data collection

    np_max-act · gemini-2.0-flash

    The neuron flags sentences that enumerate or define the contents of a resource—e.g. lines using verbs like “includes,” “contains,” or “information about” to list what’s in a database or vocabulary.

    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
     میلیون
    -0.07
     matures
    -0.06
     screening
    -0.06
     które
    -0.06
     Accord
    -0.06
    ank
    -0.06
     Su
    -0.06
     genotype
    -0.06
    iscrim
    -0.06
     Bulld
    -0.06
    POSITIVE LOGITS
     smarty
    0.07
    üme
    0.07
    ','=','
    0.07
    =\"/
    0.07
    =length
    0.07
    :i
    0.06
    NetMessage
    0.06
    età
    0.06
    .Fire
    0.06
     Monad
    0.06
    Activations Density 0.028%

    No Known Activations