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. 19-RESID-POST-AA
    6. 9821
    Prev
    Next
    INDEX
    Explanations

    know

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     výro
    -0.07
     Lazar
    -0.06
    enco
    -0.06
    balance
    -0.06
     면
    -0.06
    унк
    -0.06
    ignon
    -0.06
    angling
    -0.06
    τού
    -0.06
    egen
    -0.06
    POSITIVE LOGITS
    _bd
    0.07
    多い
    0.06
    /stat
    0.06
    alet
    0.06
    TestCategory
    0.06
     Breitbart
    0.06
    HomeAs
    0.06
    (pid
    0.06
     dumpsters
    0.06
    :Is
    0.06
    Activations Density 0.004%

    No Known Activations