© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 27-RESID-POST-AA
    11. 58075
    Prev
    Next
    INDEX
    Explanations

    want

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     университ
    -0.07
    	expected
    -0.07
    ente
    -0.07
    ents
    -0.06
    }},↵
    -0.06
     Seasons
    -0.06
    Ul
    -0.06
     Agriculture
    -0.06
     СССР
    -0.06
    cribe
    -0.06
    POSITIVE LOGITS
    (DIS
    0.07
    ="<
    0.06
     open
    0.06
     cocos
    0.06
     mrt
    0.06
    userRepository
    0.06
    unlikely
    0.06
    .Metadata
    0.06
     dma
    0.06
    .life
    0.05
    Activations Density 0.033%

    No Known Activations