© 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. 23-RESID-POST-AA
    11. 64091
    Prev
    Next
    INDEX
    Explanations

    168

    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_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DataMember
    -0.06
    ่ว
    -0.06
    	verify
    -0.06
     ble
    -0.06
    opies
    -0.06
    .Last
    -0.06
    imde
    -0.06
    .All
    -0.06
    ิจ
    -0.06
    .addValue
    -0.06
    POSITIVE LOGITS
     plunder
    0.08
     wound
    0.07
     leo
    0.07
    510
    0.07
    -weight
    0.07
    168
    0.07
    .robot
    0.07
    108
    0.06
     paar
    0.06
    协议
    0.06
    Activations Density 0.011%

    No Known Activations