© 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. 15-RESID-POST-AA
    11. 45663
    Prev
    Next
    INDEX
    Explanations

    .r

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     subtraction
    -0.07
    (Mock
    -0.06
    bon
    -0.06
    infile
    -0.06
    ;++
    -0.06
    θήκη
    -0.06
    $IFn
    -0.06
    (ret
    -0.06
     expend
    -0.06
     Từ
    -0.06
    POSITIVE LOGITS
     сосуд
    0.07
     tackle
    0.07
     coaches
    0.06
     autistic
    0.06
    لعاب
    0.06
     skirt
    0.06
     }\
    0.06
     있고
    0.06
     Ever
    0.06
     Pars
    0.06
    Activations Density 0.008%

    No Known Activations