© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 59027
    Prev
    Next
    INDEX
    Explanations

    tildes

    np_max-act · gemini-2.0-flash

    This neuron responds to numeric expressions—digits, decimal values, and formula‐like tokens—within the text.

    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
     Gale
    -0.07
     coined
    -0.07
    credited
    -0.07
     tbl
    -0.07
    TeX
    -0.06
     curb
    -0.06
    zan
    -0.06
    Containers
    -0.06
     Ray
    -0.06
    Ruby
    -0.06
    POSITIVE LOGITS
    除了
    0.08
     галуз
    0.08
     Eylül
    0.07
    월부터
    0.07
    .middle
    0.07
     Kasım
    0.07
     confort
    0.06
     �
    0.06
    MASK
    0.06
    ามารถ
    0.06
    Activations Density 0.152%

    No Known Activations