© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 72668
    Prev
    Next
    INDEX
    Explanations

    the

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ges
    -0.07
    .documents
    -0.07
    -can
    -0.06
    (click
    -0.06
    ysics
    -0.06
     والد
    -0.06
    ancer
    -0.06
    -Based
    -0.06
     inconsistency
    -0.06
    шел
    -0.06
    POSITIVE LOGITS
     onze
    0.07
     dvoj
    0.07
    func
    0.06
     appointed
    0.06
    .savefig
    0.06
     _____
    0.06
     bắt
    0.06
    感じ
    0.06
     kèm
    0.06
    .Timeout
    0.06
    Activations Density 0.077%

    No Known Activations