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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 21343
    Prev
    Next
    INDEX
    Explanations

    chemical processes

    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
    شي
    -0.06
     Connecticut
    -0.06
     vil
    -0.06
    헤
    -0.06
    drink
    -0.06
    ни
    -0.06
    .DE
    -0.06
    .percent
    -0.06
     mül
    -0.05
     volunteer
    -0.05
    POSITIVE LOGITS
    orz
    0.08
     preamble
    0.07
     застосування
    0.07
     sparking
    0.06
    imetype
    0.06
    Handler
    0.06
     lég
    0.06
    .mContext
    0.06
     pageCount
    0.06
     embody
    0.06
    Activations Density 0.089%

    No Known Activations