© 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. 35848
    Prev
    Next
    INDEX
    Explanations

    except

    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
     decimal
    -0.08
    ;++
    -0.07
     heightFor
    -0.07
     clad
    -0.07
    >";
↵
    -0.07
    瑞
    -0.07
    />.
    -0.06
    (det
    -0.06
     yardım
    -0.06
    юдж
    -0.06
    POSITIVE LOGITS
     마지막
    0.07
    adní
    0.07
    ISP
    0.07
    只要
    0.07
     erotisch
    0.06
     Around
    0.06
    اته
    0.06
     around
    0.06
    icho
    0.06
    .Common
    0.06
    Activations Density 0.001%

    No Known Activations