© 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. 3-RESID-POST-AA
    11. 123268
    Prev
    Next
    INDEX
    Explanations

    anda

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     prvním
    -0.08
    افع
    -0.07
    abilir
    -0.07
     involving
    -0.07
     새로운
    -0.07
    ภาษ
    -0.07
    _repeat
    -0.06
    ために
    -0.06
    -г
    -0.06
     پن
    -0.06
    POSITIVE LOGITS
     Anda
    0.18
     saya
    0.17
     mereka
    0.16
     kita
    0.15
     anda
    0.13
     شما
    0.11
     خود
    0.09
     kami
    0.09
     μου
    0.09
     σας
    0.09
    Activations Density 0.002%

    No Known Activations