© 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. 25034
    Prev
    Next
    INDEX
    Explanations

    Japanese

    np_max-act · gemini-2.0-flash

    This neuron responds to Japanese text—especially hiragana and katakana tokens (often word‐ending particles or inflectional endings) indicating it’s spotting Japanese script.

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

    technical terms related to programming and memory management.

    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
    Kyle
    -0.08
    Import
    -0.07
     Dios
    -0.07
    /'+
    -0.07
     Armour
    -0.07
     Deus
    -0.07
    Zone
    -0.07
     debates
    -0.06
     lact
    -0.06
    quoi
    -0.06
    POSITIVE LOGITS
    ふ
    0.08
     pervasive
    0.07
    .",
    ↵
    0.07
    inkle
    0.06
    _OVERFLOW
    0.06
     않는
    0.06
    historic
    0.06
    _blocks
    0.06
    овор
    0.06
    �
    0.06
    Activations Density 0.032%

    No Known Activations