© 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. 7503
    Prev
    Next
    INDEX
    Explanations

    Internet text

    np_max-act · gemini-2.0-flash

    The neuron fires on bits of text that activate or set a conversation “mode” or “style” (e.g. tokens like “active,” “style,” “conversation,” “mode,” “activé,” etc.).

    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
     Addr
    -0.07
    /book
    -0.07
    annels
    -0.06
    เทคโนโลย
    -0.06
     goals
    -0.06
    ادی
    -0.06
     sands
    -0.06
    ymous
    -0.06
    wpdb
    -0.06
     Tep
    -0.06
    POSITIVE LOGITS
     září
    0.07
    間
    0.06
    一区
    0.06
    ("{\"
    0.06
     жод
    0.06
    _image
    0.06
     ledna
    0.06
    šem
    0.06
    영어
    0.06
    ][]
    0.06
    Activations Density 0.021%

    No Known Activations