© 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. 27-RESID-POST-AA
    11. 9780
    Prev
    Next
    INDEX
    Explanations

    Instructions

    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
     database
    -0.08
    ropolis
    -0.07
     ourselves
    -0.07
     struck
    -0.07
     airplanes
    -0.06
    ','#
    -0.06
     historian
    -0.06
    ↵    ↵
    -0.06
     critic
    -0.06
     secured
    -0.06
    POSITIVE LOGITS
    ευ
    0.07
     блю
    0.06
     sightings
    0.06
    wal
    0.06
    ày
    0.06
    668
    0.06
    amaha
    0.06
    ουν
    0.06
     destinationViewController
    0.06
     було
    0.06
    Activations Density 0.060%

    No Known Activations