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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 24751
    Prev
    Next
    INDEX
    Explanations

    area

    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
    σμ
    -0.07
     raining
    -0.06
    embr
    -0.06
     이야
    -0.06
    �
    -0.06
    mental
    -0.06
    thumb
    -0.06
     다시
    -0.06
     تبد
    -0.06
     riff
    -0.06
    POSITIVE LOGITS
     setType
    0.08
    .setLayout
    0.07
    imeters
    0.07
     Čes
    0.06
    Ö
    0.06
    ->$
    0.06
     березня
    0.06
    -interface
    0.06
     target
    0.06
     THREE
    0.06
    Activations Density 0.000%

    No Known Activations