© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 54057
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns

    np_max-act · gemini-2.0-flash

    The neuron fires on individual words naming technical processes or operations (e.g. “processing,” “coding,” “broadcast,” “calibrate,” “javascript,” “camp,” etc.).

    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
    cede
    -0.06
    _LINES
    -0.06
     Comp
    -0.06
     Phen
    -0.06
     idiot
    -0.06
     furthermore
    -0.06
    Compound
    -0.06
    -delete
    -0.06
    .destination
    -0.06
     Posts
    -0.06
    POSITIVE LOGITS
    database
    0.07
     своє
    0.07
     Aş
    0.06
     Swift
    0.06
    šit
    0.06
    =[
    0.06
    』
    0.06
    ！↵↵
    0.06
    ."</
    0.06
    .Symbol
    0.06
    Activations Density 0.091%

    No Known Activations