© 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. 27-RESID-POST-AA
    11. 12122
    Prev
    Next
    INDEX
    Explanations

    too

    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
     chilled
    -0.07
     Chest
    -0.06
    STDOUT
    -0.06
     сама
    -0.06
    _frag
    -0.06
     mastery
    -0.06
    -prefix
    -0.06
    -square
    -0.06
     Inspection
    -0.06
    Forest
    -0.06
    POSITIVE LOGITS
    (ar
    0.07
    ké
    0.06
     ↵        ↵
    0.06
     влас
    0.06
    ubby
    0.06
     अगल
    0.06
     이렇게
    0.06
    "Do
    0.06
    요일
    0.06
    �
    0.06
    Activations Density 0.044%

    No Known Activations