© 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. 101313
    Prev
    Next
    INDEX
    Explanations

    conveying information

    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
    ();
↵
    -0.08
    .ResumeLayout
    -0.07
    ACA
    -0.07
    plets
    -0.07
     carbonate
    -0.07
    simp
    -0.06
     bore
    -0.06
    RESET
    -0.06
     activated
    -0.06
    Shoot
    -0.06
    POSITIVE LOGITS
    erring
    0.07
     postage
    0.07
    ('@
    0.06
    -league
    0.06
    scription
    0.06
     Cornell
    0.06
    ]‏
    0.06
    .SelectedIndexChanged
    0.06
     เค
    0.06
    cházet
    0.06
    Activations Density 0.032%

    No Known Activations