© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 27-RESID-POST-AA
    11. 113743
    Prev
    Next
    INDEX
    Explanations

    Hidden or subtle actions

    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
    眠
    -0.07
    -terminal
    -0.07
    (k
    -0.07
     包
    -0.07
     Memory
    -0.07
    ########
    -0.06
     akci
    -0.06
    _VER
    -0.06
    ्र
    -0.06
    -blocking
    -0.06
    POSITIVE LOGITS
     caster
    0.07
    /run
    0.06
     sizi
    0.06
     Submitted
    0.06
    interest
    0.06
    HasColumnName
    0.06
    องจาก
    0.06
     MQ
    0.06
    能力
    0.06
    (news
    0.06
    Activations Density 0.044%

    No Known Activations