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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 58880
    Prev
    Next
    INDEX
    Explanations

    Future actions/tense

    np_max-act · gemini-2.0-flash

    conversational prompts that encourage playful and engaging interactions.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron detects user‐issued directives or change‐of‐context instructions (e.g., “From now on, I want you to…”).

    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
    .tables
    -0.07
     آی
    -0.07
    _,↵
    -0.07
    莫
    -0.07
     avis
    -0.07
    Skills
    -0.06
    ADDING
    -0.06
     comment
    -0.06
    HORT
    -0.06
    อาย
    -0.06
    POSITIVE LOGITS
    вание
    0.07
     tegen
    0.07
    оть
    0.06
     دسته
    0.06
    Cookie
    0.06
    違
    0.05
    -awesome
    0.05
    ційний
    0.05
     Adobe
    0.05
     Outside
    0.05
    Activations Density 0.021%

    No Known Activations