© 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. 19-RESID-POST-AA
    11. 72730
    Prev
    Next
    INDEX
    Explanations

    network security

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ives
    -0.08
    خذ
    -0.07
    dw
    -0.07
    ive
    -0.07
     Rw
    -0.06
    �
    -0.06
    _LOC
    -0.06
     sobie
    -0.06
    LocalStorage
    -0.06
     Char
    -0.06
    POSITIVE LOGITS
     allowing
    0.07
     participating
    0.07
     ESPN
    0.06
     IOException
    0.06
     astronomical
    0.06
    identification
    0.06
     کیل
    0.06
    (pred
    0.06
     deser
    0.06
     microbial
    0.06
    Activations Density 0.016%

    No Known Activations