© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 19-RESID-POST-AA
    11. 114221
    Prev
    Next
    INDEX
    Explanations

    Aw

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .Spring
    -0.07
    ,readonly
    -0.06
    овани
    -0.06
     نگهداری
    -0.06
    .project
    -0.06
    .constraints
    -0.06
     dần
    -0.06
    (storage
    -0.06
    (tuple
    -0.06
    ('{}
    -0.06
    POSITIVE LOGITS
     Aw
    0.09
     AIM
    0.08
    Aw
    0.08
    Alt
    0.08
    WP
    0.07
     Ap
    0.07
     parentheses
    0.07
     Unused
    0.07
     ﾄ
    0.07
     WD
    0.07
    Activations Density 0.007%

    No Known Activations