© 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. 61498
    Prev
    Next
    INDEX
    Explanations

    secure packaging

    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
    ств
    -0.07
     mixer
    -0.06
     BitConverter
    -0.06
    ANGE
    -0.06
    essed
    -0.06
     wealthy
    -0.06
    ्फ
    -0.06
    지고
    -0.06
    (hObject
    -0.06
    LE
    -0.06
    POSITIVE LOGITS
     alumno
    0.06
    creates
    0.06
     만들
    0.06
     sosyal
    0.06
     mathematic
    0.06
     Japon
    0.06
     कब
    0.06
     öğretmen
    0.06
     realiza
    0.06
    QQ
    0.06
    Activations Density 0.201%

    No Known Activations