© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 95691
    Prev
    Next
    INDEX
    Explanations

    895

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    318
    -0.08
    665
    -0.07
    _no
    -0.07
    حل
    -0.07
    661
    -0.07
    ۱۰
    -0.07
    incess
    -0.07
     Reflect
    -0.07
    66
    -0.07
    474
    -0.07
    POSITIVE LOGITS
    890
    0.23
    895
    0.22
    891
    0.20
    893
    0.19
    894
    0.18
    898
    0.18
    897
    0.18
    892
    0.17
    896
    0.17
    899
    0.16
    Activations Density 0.002%

    No Known Activations