© 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. 11-RESID-POST-AA
    6. 74850
    Prev
    Next
    INDEX
    Explanations

    breaks and stopping points

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <Result
    -0.07
     unarmed
    -0.07
     calcular
    -0.06
            
    -0.06
    gra
    -0.06
     Liverpool
    -0.06
    charm
    -0.05
     Kar
    -0.05
    قلال
    -0.05
     přátel
    -0.05
    POSITIVE LOGITS
     Contin
    0.07
     захоп
    0.07
     getColumn
    0.06
    lamp
    0.06
     product
    0.06
    ufac
    0.06
     manière
    0.06
     yaz
    0.06
    emu
    0.06
     slick
    0.06
    Activations Density 0.070%

    No Known Activations