© 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. 15-RESID-POST-AA
    11. 32705
    Prev
    Next
    INDEX
    Explanations

    Legal affirmations/denials

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     attends
    -0.08
     problems
    -0.08
     fashionable
    -0.06
     devam
    -0.06
     verified
    -0.06
     unpredict
    -0.06
     lat
    -0.06
     lugar
    -0.06
     problem
    -0.06
     Wrapper
    -0.06
    POSITIVE LOGITS
    薬
    0.07
    (OP
    0.07
     anatomy
    0.07
    В
    0.06
     TestBed
    0.06
    itive
    0.06
    >p
    0.06
    rec
    0.06
    editable
    0.06
     surgical
    0.06
    Activations Density 0.020%

    No Known Activations