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. 7-RESID-POST-AA
    6. 72221
    Prev
    Next
    INDEX
    Explanations

    encourage

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pretrained
    -0.07
    Plate
    -0.06
    ентів
    -0.06
    |RF
    -0.06
    ражд
    -0.06
    Indexed
    -0.06
     Jacket
    -0.06
    HeadersHeight
    -0.06
    .img
    -0.06
     briefed
    -0.06
    POSITIVE LOGITS
     failures
    0.06
     Ur
    0.06
     filter
    0.06
     رم
    0.06
     assigning
    0.06
     Tunis
    0.06
     values
    0.06
     아이콘
    0.06
     چنین
    0.06
    ··
    0.06
    Activations Density 0.157%

    No Known Activations