© 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
    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. 68415
    Prev
    Next
    INDEX
    Explanations

    up

    np_max-act · gemini-2.0-flash

    This neuron activates on phrasing that instructs the model to “make up” or fabricate information.

    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
     Items
    -0.06
    елен
    -0.06
    Ram
    -0.06
     PureComponent
    -0.06
    .IMAGE
    -0.06
     застав
    -0.06
     XS
    -0.06
    �示
    -0.06
    avid
    -0.06
     Radiation
    -0.06
    POSITIVE LOGITS
    [jj
    0.08
     velik
    0.07
    _ED
    0.07
     epilepsy
    0.07
     osc
    0.07
    _pod
    0.07
    [num
    0.07
    _employee
    0.06
    -|
    0.06
    .getP
    0.06
    Activations Density 0.002%

    No Known Activations