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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 122982
    Prev
    Next
    INDEX
    Explanations

    copies

    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
    .getLabel
    -0.07
    PEnd
    -0.07
    (com
    -0.06
     próxima
    -0.06
     Divine
    -0.06
     City
    -0.06
     Direct
    -0.06
    (custom
    -0.06
    ЕР
    -0.06
    alpha
    -0.06
    POSITIVE LOGITS
     داو
    0.06
    _VERIFY
    0.06
    ант
    0.06
    \Domain
    0.06
    ृत
    0.06
    -Compatible
    0.06
    OPTIONS
    0.06
    �
    0.06
    _keywords
    0.06
    ログ
    0.06
    Activations Density 0.001%

    No Known Activations