Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 53844
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
    ulled
    -0.06
    .City
    -0.06
    /calendar
    -0.06
    getStore
    -0.06
    Bucket
    -0.06
    _RESERVED
    -0.06
    11
    -0.06
    monkey
    -0.06
    .Yellow
    -0.06
    .qq
    -0.06
    POSITIVE LOGITS
     carte
    0.07
     понять
    0.06
     NRL
    0.06
     rosa
    0.06
     alıyor
    0.06
     được
    0.06
    ]
    0.06
    _play
    0.06
    (href
    0.06
     réfé
    0.06
    Activations Density 0.022%

    No Known Activations