© 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. 27-RESID-POST-AA
    6. 27560
    Prev
    Next
    INDEX
    Explanations

    say "day"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     validator
    -0.08
     Parameter
    -0.08
    -saving
    -0.07
     capacities
    -0.07
     furnace
    -0.07
     discussed
    -0.07
    adders
    -0.07
    orneys
    -0.06
     philosoph
    -0.06
     Seller
    -0.06
    POSITIVE LOGITS
     भ
    0.06
     <%=
    0.06
    ีฬา
    0.06
    /NĐ
    0.06
    	State
    0.06
    (strpos
    0.06
     здоб
    0.05
    rå
    0.05
    相手
    0.05
    řich
    0.05
    Activations Density 0.036%

    No Known Activations