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. 119935
    Prev
    Next
    INDEX
    Explanations

    quotation marks

    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
    -production
    -0.07
    \Configuration
    -0.07
    �
    -0.07
     hectares
    -0.06
    currentIndex
    -0.06
    _out
    -0.06
     Production
    -0.06
    $q
    -0.06
    decorate
    -0.06
     chút
    -0.06
    POSITIVE LOGITS
     čís
    0.06
    Ill
    0.06
     Producto
    0.05
    不到
    0.05
     مناسب
    0.05
    ая
    0.05
    áln
    0.05
     بهره
    0.05
     наказ
    0.05
     nâng
    0.05
    Activations Density 0.031%

    No Known Activations