© 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. 15-RESID-POST-AA
    6. 73539
    Prev
    Next
    INDEX
    Explanations

    a

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     er
    -0.07
     tsunami
    -0.07
     lanc
    -0.07
     talent
    -0.07
    .d
    -0.07
     contrario
    -0.07
     vac
    -0.06
    ์ต
    -0.06
     lugar
    -0.06
    πος
    -0.06
    POSITIVE LOGITS
     základ
    0.06
    &apos
    0.06
     publishers
    0.06
     architect
    0.06
    indent
    0.06
    six
    0.06
    Orig
    0.06
    zkum
    0.06
    atham
    0.06
    Serialize
    0.06
    Activations Density 0.713%

    No Known Activations