© 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. 27-RESID-POST-AA
    11. 6718
    Prev
    Next
    INDEX
    Explanations

    of/the

    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
    Negative Logits
     differ
    -0.07
    (factory
    -0.06
     yield
    -0.06
    _MINUS
    -0.06
     Swords
    -0.06
     control
    -0.06
     coch
    -0.06
     TIME
    -0.06
    Quick
    -0.06
    ']).
    -0.06
    POSITIVE LOGITS
     FI
    0.06
     svou
    0.06
    일에
    0.06
    wik
    0.06
    =F
    0.06
    心理
    0.06
     GWei
    0.06
    щих
    0.06
    Lf
    0.06
     demonic
    0.06
    Activations Density 0.051%

    No Known Activations