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. 11-RESID-POST-AA
    6. 86027
    Prev
    Next
    INDEX
    Explanations

    contrast

    np_max-act · gemini-2.0-flash

    The neuron activates on terms referring to medical imaging contrast agents and related enhancement (e.g., “contrast,” “gadolinium,” “contrast‐enhanced,” “agent,” “media”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     decree
    -0.06
     pageNumber
    -0.06
    ded
    -0.06
    factor
    -0.06
     subTitle
    -0.06
     Methodist
    -0.06
    '].'"
    -0.06
    pire
    -0.06
    _LL
    -0.06
    AP
    -0.06
    POSITIVE LOGITS
    /comments
    0.06
     Giants
    0.06
     بانک
    0.06
     cooperating
    0.06
    -testid
    0.06
     Review
    0.06
    -os
    0.06
     SOLUTION
    0.06
     =(
    0.06
    _THIS
    0.06
    Activations Density 0.005%

    No Known Activations