© 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. 11-RESID-POST-AA
    11. 101143
    Prev
    Next
    INDEX
    Explanations

    Wireless/Mobile networks

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    Safety
    -0.08
    dados
    -0.06
    .epoch
    -0.06
     شکن
    -0.06
     NCAA
    -0.06
    Mass
    -0.06
    cılar
    -0.06
     workforce
    -0.06
     instead
    -0.06
     trials
    -0.06
    POSITIVE LOGITS
     keş
    0.07
    ":"+
    0.07
    ště
    0.07
    štění
    0.06
     розташ
    0.06
     '{$
    0.06
    ์:
    0.06
    _WAIT
    0.06
     unsus
    0.06
     twitch
    0.06
    Activations Density 0.068%

    No Known Activations