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. 81356
    Prev
    Next
    INDEX
    Explanations

    first

    np_max-act · gemini-2.0-flash

    The neuron spotlights occurrences of “first” in recommendation phrases (e.g. “first-line,” “first choice”) indicating a primary or initial option.

    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
    _age
    -0.07
     böylece
    -0.07
    .rotation
    -0.07
     Philosoph
    -0.06
     runnable
    -0.06
    .put
    -0.06
     Netanyahu
    -0.06
     бан
    -0.06
    .bits
    -0.06
    .Nombre
    -0.06
    POSITIVE LOGITS
    rename
    0.07
     Roch
    0.06
    п
    0.06
    ็นอ
    0.06
    (Result
    0.06
     guint
    0.06
     박
    0.06
    trip
    0.06
    icans
    0.06
    isha
    0.06
    Activations Density 0.015%

    No Known Activations