© 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. 15-RESID-POST-AA
    11. 37637
    Prev
    Next
    INDEX
    Explanations

    ib

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    くな
    -0.06
    -black
    -0.06
    	target
    -0.06
    cow
    -0.06
     ngừng
    -0.06
     فال
    -0.06
     الل
    -0.06
     bis
    -0.06
     tasarım
    -0.06
     cult
    -0.06
    POSITIVE LOGITS
    >b
    0.07
    MAP
    0.07
    .setTitle
    0.07
    >",
    0.07
    }}>
    0.06
    execute
    0.06
    Mul
    0.06
     spor
    0.06
    umi
    0.06
     gioc
    0.06
    Activations Density 0.000%

    No Known Activations