© 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. 7-RESID-POST-AA
    11. 76867
    Prev
    Next
    INDEX
    Explanations

    auction

    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
     libro
    -0.08
     stabilize
    -0.07
    desktop
    -0.07
     Hizmetleri
    -0.07
     plank
    -0.07
    porte
    -0.06
     DAMAGE
    -0.06
    __()
    -0.06
     MED
    -0.06
    clid
    -0.06
    POSITIVE LOGITS
     auction
    0.17
     Auction
    0.13
     auctions
    0.13
    auction
    0.10
    
    0.07
     Austin
    0.06
     mentions
    0.06
    Austin
    0.06
    057
    0.06
    "><?=
    0.06
    Activations Density 0.002%

    No Known Activations