© 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. 74089
    Prev
    Next
    INDEX
    Explanations

    topical

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of “topical” (i.e. references to topical application or topical treatments).

    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
     lung
    -0.08
    z
    -0.07
    raham
    -0.07
     rotation
    -0.07
    Sz
    -0.07
    dz
    -0.07
    .biz
    -0.06
    -dashboard
    -0.06
     ciz
    -0.06
    caffold
    -0.06
    POSITIVE LOGITS
     topical
    0.09
    顶
    0.07
    モデル
    0.07
    odem
    0.07
    IPH
    0.07
     місцев
    0.07
    ęp
    0.06
    OP
    0.06
    مول
    0.06
    	JOptionPane
    0.06
    Activations Density 0.001%

    No Known Activations