© 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. 91308
    Prev
    Next
    INDEX
    Explanations

    0

    np_max-act · gemini-2.0-flash

    technical elements related to game object properties in a programming context.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron flags numeric literal tokens—especially floating‐point values—in the serialized file.

    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
    tik
    -0.07
    Poor
    -0.06
    TG
    -0.06
    いう
    -0.06
    getObject
    -0.06
     poor
    -0.06
    ря
    -0.06
    Very
    -0.06
    cw
    -0.06
     Abr
    -0.06
    POSITIVE LOGITS
     éc
    0.07
    jure
    0.07
    :@"%@",
    0.06
     έχ
    0.06
    -file
    0.06
    -ft
    0.06
     감
    0.06
     yiy
    0.06
     ail
    0.06
     心
    0.06
    Activations Density 0.003%

    No Known Activations