© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 23-RESID-POST-AA
    11. 68943
    Prev
    Next
    INDEX
    Explanations

    저

    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_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    units
    -0.07
     elemento
    -0.07
     elementos
    -0.07
    approximately
    -0.07
    Rightarrow
    -0.06
    Unit
    -0.06
     Preston
    -0.06
     Sle
    -0.06
    enido
    -0.06
    效果
    -0.06
    POSITIVE LOGITS
    借
    0.07
     IDS
    0.07
    관리
    0.07
     Export
    0.07
    ]/
    0.07
    )<
    0.06
    ricao
    0.06
    müş
    0.06
     змож
    0.06
    _ATTACK
    0.06
    Activations Density 0.001%

    No Known Activations