© 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. 99980
    Prev
    Next
    INDEX
    Explanations

    at

    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
     crochet
    -0.07
     claws
    -0.07
    .buy
    -0.06
    ayı
    -0.06
    Directed
    -0.06
    аніз
    -0.06
    لیسی
    -0.06
    eenth
    -0.06
    cliente
    -0.06
    chemes
    -0.06
    POSITIVE LOGITS
     k�
    0.06
     저
    0.06
    .adjust
    0.06
     emo
    0.06
     klid
    0.06
    .BASE
    0.06
     repmat
    0.06
     SIL
    0.06
    웠
    0.06
    	opts
    0.06
    Activations Density 0.022%

    No Known Activations