© 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. 57033
    Prev
    Next
    INDEX
    Explanations

    Not serious or a threat

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Watches
    -0.06
     Authentic
    -0.06
    Videos
    -0.06
     حص
    -0.06
     Austr
    -0.06
     swords
    -0.06
    aky
    -0.06
    從
    -0.06
     سو
    -0.06
    从
    -0.06
    POSITIVE LOGITS
    =msg
    0.07
     Lumia
    0.07
     lumber
    0.06
     "+↵
    0.06
    -browser
    0.06
    ंगठन
    0.06
     Влади
    0.06
     Destructor
    0.06
    ISO
    0.06
     ए
    0.06
    Activations Density 0.081%

    No Known Activations