© 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
    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. 92259
    Prev
    Next
    INDEX
    Explanations

    as

    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
    Fail
    -0.07
    .keys
    -0.06
    etě
    -0.06
    烧
    -0.06
     Mortgage
    -0.06
    ydı
    -0.06
     optimizations
    -0.06
    background
    -0.06
    INTEGER
    -0.06
    属
    -0.06
    POSITIVE LOGITS
    ●●●●●●●●●●●●●●●●
    0.06
    घ
    0.06
     downwards
    0.06
     цент
    0.06
    atsby
    0.06
     graceful
    0.06
    จากการ
    0.06
     عنه
    0.06
    下载次数
    0.06
     механіз
    0.06
    Activations Density 0.019%

    No Known Activations