© 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. 36715
    Prev
    Next
    INDEX
    Explanations

    club

    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
     assertEquals
    -0.07
     будь
    -0.07
    τω
    -0.06
    	attack
    -0.06
     synt
    -0.06
    .Result
    -0.06
    해요
    -0.06
     irradi
    -0.06
     державної
    -0.06
     possibilities
    -0.06
    POSITIVE LOGITS
    ”。↵↵
    0.08
     Clubs
    0.07
     clubs
    0.07
     club
    0.07
     therapists
    0.07
     province
    0.07
     лишь
    0.07
     chap
    0.06
     chapel
    0.06
     clr
    0.06
    Activations Density 0.004%

    No Known Activations