© 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. 7-RESID-POST-AA
    11. 79576
    Prev
    Next
    INDEX
    Explanations

    was

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     abl
    -0.06
     поли
    -0.06
    нина
    -0.06
     astronaut
    -0.06
     Finland
    -0.06
     mg
    -0.06
    xlim
    -0.06
    ctrl
    -0.06
    ич
    -0.06
    pec
    -0.06
    POSITIVE LOGITS
     employing
    0.07
     intimately
    0.07
     จำ
    0.07
     personel
    0.07
    .onNext
    0.06
     amazing
    0.06
     educ
    0.06
     για
    0.06
    .AR
    0.06
     backpage
    0.06
    Activations Density 0.015%

    No Known Activations