© 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. 11-RESID-POST-AA
    11. 101197
    Prev
    Next
    INDEX
    Explanations

    question answering

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    .cls
    -0.07
     DMA
    -0.07
     offences
    -0.06
    .WindowManager
    -0.06
    _CONF
    -0.06
    ushort
    -0.06
     //_
    -0.06
     minds
    -0.06
    getDb
    -0.06
    ायक
    -0.06
    POSITIVE LOGITS
    ливо
    0.06
     obvykle
    0.06
     fed
    0.06
     fairly
    0.06
     nigeria
    0.06
     managing
    0.06
    uteč
    0.06
     kinda
    0.06
     unins
    0.06
     looks
    0.06
    Activations Density 0.064%

    No Known Activations