© 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. 7-RESID-POST-AA
    11. 96342
    Prev
    Next
    INDEX
    Explanations

    for

    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
     jar
    -0.07
     Wax
    -0.07
     Gaza
    -0.07
     Chern
    -0.07
    λέον
    -0.07
    幕
    -0.06
     antenna
    -0.06
     Dominion
    -0.06
    -too
    -0.06
     antennas
    -0.06
    POSITIVE LOGITS
    (base
    0.07
    .She
    0.06
     Deletes
    0.06
    чается
    0.06
     collaborations
    0.06
    :req
    0.06
    (Response
    0.06
     вважа
    0.06
    μένων
    0.06
    _URI
    0.06
    Activations Density 0.068%

    No Known Activations