© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 6356
    Prev
    Next
    INDEX
    Explanations

    remodeling

    np_max-act · gemini-2.0-flash

    This neuron activates on mentions of remodeling or renovation (e.g., “remodel,” “remodeling,” “renovation”) in home‐improvement contexts.

    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
     GK
    -0.07
    ंपर
    -0.07
    真正
    -0.06
    柴
    -0.06
     biçim
    -0.06
    озна
    -0.06
    lm
    -0.06
     Psalm
    -0.06
    (Player
    -0.06
     News
    -0.06
    POSITIVE LOGITS
    -multi
    0.06
     closures
    0.06
    :YES
    0.06
    ateful
    0.06
    stash
    0.06
    _rev
    0.06
    ADE
    0.06
    atu
    0.06
     faut
    0.06
    ichten
    0.06
    Activations Density 0.008%

    No Known Activations