© 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. 3-RESID-POST-AA
    11. 95851
    Prev
    Next
    INDEX
    Explanations

    vestib

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    flu
    -0.07
    -al
    -0.07
    灰
    -0.06
    Fr
    -0.06
     ガ
    -0.06
    Figure
    -0.06
    703
    -0.06
    相
    -0.06
    ½
    -0.06
     corros
    -0.06
    POSITIVE LOGITS
     vestib
    0.31
     listItem
    0.06
    ib
    0.06
    	actor
    0.06
    .ColumnStyles
    0.06
    .pub
    0.06
     escorte
    0.06
    	ob
    0.06
    amespace
    0.06
    (enabled
    0.06
    Activations Density 0.000%

    No Known Activations