© 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. 77948
    Prev
    Next
    INDEX
    Explanations

    programming and databases

    np_max-act · gemini-2.0-flash

    This neuron responds to programming-related tokens—class/library names, API calls, and other code identifiers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    technical issues related to database encoding and character sets.

    oai_token-act-pair · gpt-4o-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
    healthy
    -0.07
     nothing
    -0.06
     migrants
    -0.06
     enviar
    -0.06
    gni
    -0.06
    限制
    -0.06
    θ
    -0.06
    games
    -0.06
     tiến
    -0.06
    >())↵
    -0.06
    POSITIVE LOGITS
     gül
    0.06
     Aph
    0.06
     oldukça
    0.06
     ResultSet
    0.06
     thuộc
    0.06
    κολ
    0.06
    属于
    0.06
     tweets
    0.06
    .Ph
    0.06
    -bar
    0.06
    Activations Density 0.130%

    No Known Activations