© 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. 30827
    Prev
    Next
    INDEX
    Explanations

    mathematics

    np_max-act · gemini-2.0-flash

    This neuron does not respond to any tokens and remains inactive, i.e., it does not detect any particular pattern.

    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
    loading
    -0.08
     RowBox
    -0.08
    INSTALL
    -0.07
    ?("
    -0.07
     правиль
    -0.07
     Bronze
    -0.06
     Σχ
    -0.06
    PropertyDescriptor
    -0.06
     Bryce
    -0.06
     {'
    -0.06
    POSITIVE LOGITS
     Dani
    0.06
     etkin
    0.06
     вари
    0.06
     νεφοκάλυψης
    0.06
     primary
    0.06
     بودن
    0.06
     Till
    0.06
     socialist
    0.05
     dbl
    0.05
     Sommer
    0.05
    Activations Density 0.008%

    No Known Activations