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. 111452
    Prev
    Next
    INDEX
    Explanations

    legal language

    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
    906
    -0.06
    _DELTA
    -0.06
    _urls
    -0.06
     medium
    -0.06
    Tiles
    -0.06
     возраста
    -0.06
    SingleNode
    -0.06
    часно
    -0.06
     textiles
    -0.06
    706
    -0.06
    POSITIVE LOGITS
    ività
    0.07
     ].
    0.07
     Humanity
    0.07
     CNBC
    0.06
    _CERT
    0.06
    дать
    0.06
    LARI
    0.06
    (Note
    0.06
    edik
    0.06
     hos
    0.06
    Activations Density 0.031%

    No Known Activations