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

    Neuronpedia

    APICircuit 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. 123553
    Prev
    Next
    INDEX
    Explanations

    Programming/technical documentation

    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
     seconds
    -0.07
    acman
    -0.06
     bullish
    -0.06
    님
    -0.06
    Titulo
    -0.06
    ало
    -0.06
    če
    -0.06
     Act
    -0.06
    )obj
    -0.06
    give
    -0.06
    POSITIVE LOGITS
     finite
    0.07
     danske
    0.07
     �
    0.07
    :Set
    0.07
     نزد
    0.06
    ural
    0.06
    貼
    0.06
    EEP
    0.06
     unfolded
    0.06
     SOLUTION
    0.06
    Activations Density 0.075%

    No Known Activations