© 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. 47753
    Prev
    Next
    INDEX
    Explanations

    Formal text/documentation

    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
    Not in Any Lists

    No Comments

    Negative Logits
    seek
    -0.06
    ूष
    -0.06
    	This
    -0.06
     bud
    -0.06
    _Un
    -0.06
     Amazing
    -0.06
    /static
    -0.06
     /*!↵
    -0.05
    пон
    -0.05
    uka
    -0.05
    POSITIVE LOGITS
     internal
    0.08
     Checked
    0.07
     competent
    0.07
     полі
    0.07
     rej
    0.07
    Investigators
    0.07
     gehört
    0.06
     justified
    0.06
     substitutions
    0.06
     genocide
    0.06
    Activations Density 0.000%

    No Known Activations