© 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 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. 20441
    Prev
    Next
    INDEX
    Explanations

    coming out

    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
     manager
    -0.07
    (sh
    -0.07
     función
    -0.06
     Recru
    -0.06
     politik
    -0.06
     dynasty
    -0.06
     translates
    -0.06
     Stable
    -0.06
     head
    -0.06
    條
    -0.06
    POSITIVE LOGITS
    noc
    0.07
     quasi
    0.07
     awareness
    0.06
     دولتی
    0.06
    	Route
    0.06
    无码
    0.06
     благ
    0.06
    _Il
    0.06
     columnName
    0.06
    .DeepEqual
    0.06
    Activations Density 0.012%

    No Known Activations