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. 81091
    Prev
    Next
    INDEX
    Explanations

    ,

    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
    ۱۹۶
    -0.06
     ')↵
    -0.06
     comple
    -0.06
    )row
    -0.06
    >null
    -0.06
     หร
    -0.05
     ECC
    -0.05
    _TOPIC
    -0.05
     بازار
    -0.05
    -ra
    -0.05
    POSITIVE LOGITS
     analytical
    0.07
    Jennifer
    0.07
    vascular
    0.07
     sophisticated
    0.07
     Conserv
    0.07
     succeeding
    0.07
    グル
    0.07
    ski
    0.07
    Girls
    0.07
     अभ
    0.07
    Activations Density 0.000%

    No Known Activations