© 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. 7-RESID-POST-AA
    6. 125690
    Prev
    Next
    INDEX
    Explanations

    screen

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Baldwin
    -0.08
    #:
    -0.07
    separator
    -0.07
    エル
    -0.07
    ��
    -0.07
     начале
    -0.06
    values
    -0.06
     Gray
    -0.06
    ----
    -0.06
    -at
    -0.06
    POSITIVE LOGITS
     Argument
    0.07
    Broadcast
    0.07
    Print
    0.06
    .EXIT
    0.06
     خطر
    0.06
     disg
    0.06
    _CONTACT
    0.06
    _Array
    0.06
    "]){↵
    0.06
    _timeline
    0.06
    Activations Density 0.000%

    No Known Activations