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. 27-RESID-POST-AA
    6. 9380
    Prev
    Next
    INDEX
    Explanations

    transcript

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    service
    -0.07
    Why
    -0.07
     outage
    -0.07
     expansion
    -0.07
    frog
    -0.07
     rubbed
    -0.06
     sofa
    -0.06
    cdot
    -0.06
    WHAT
    -0.06
    Address
    -0.06
    POSITIVE LOGITS
     getContext
    0.07
     можуть
    0.07
    aliz
    0.07
     ภาษ
    0.07
     gratuitement
    0.06
    مة
    0.06
     distributes
    0.06
    \xff
    0.06
    "]=="
    0.06
     genomic
    0.06
    Activations Density 0.002%

    No Known Activations