© 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. 126082
    Prev
    Next
    INDEX
    Explanations

    always

    np_max-act · gemini-2.0-flash

    The neuron primarily detects the adverb “always.”

    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
    Chapter
    -0.08
    >H
    -0.07
    ToggleButton
    -0.06
    Carbon
    -0.06
    spo
    -0.06
     запис
    -0.06
     Horny
    -0.06
     battled
    -0.06
     orb
    -0.06
     Bingo
    -0.06
    POSITIVE LOGITS
    结
    0.06
    uche
    0.06
    mue
    0.06
    主人
    0.06
     �
    0.06
     tải
    0.06
    ğmen
    0.06
    自治
    0.06
    :]:↵
    0.06
    _book
    0.06
    Activations Density 0.013%

    No Known Activations