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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 30563
    Prev
    Next
    INDEX
    Explanations

    #

    np_max-act · gemini-2.0-flash

    The neuron activates on speaker‐label and control tokens (e.g. “NAME_1,” “NAME_2,” brackets and markers), i.e. metadata labeling who’s speaking.

    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
     кост
    -0.07
     июня
    -0.07
    hPa
    -0.07
    _bt
    -0.07
     листопада
    -0.07
     Пред
    -0.06
     hPa
    -0.06
     subpo
    -0.06
    вай
    -0.06
    Retry
    -0.06
    POSITIVE LOGITS
    ああ
    0.07
     تاثیر
    0.06
    .timedelta
    0.06
     seulement
    0.06
    .UInt
    0.06
    特別
    0.06
     ''),↵
    0.06
    getElement
    0.05
     Org
    0.05
    .radioButton
    0.05
    Activations Density 0.005%

    No Known Activations