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. 86124
    Prev
    Next
    INDEX
    Explanations

    need to

    np_max-act · gemini-2.0-flash

    This neuron fires on words expressing requirement or necessity (e.g. need, have to, must).

    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
     Radius
    -0.06
    (Project
    -0.06
    pokemon
    -0.06
    าต
    -0.06
     trip
    -0.06
     referencia
    -0.06
    -health
    -0.06
    난
    -0.06
    (report
    -0.06
     схем
    -0.06
    POSITIVE LOGITS
     Đào
    0.07
     التع
    0.06
     depicting
    0.06
     месяцев
    0.06
     WANT
    0.06
    ş
    0.06
    ,再
    0.06
    tea
    0.06
    」的
    0.06
    .ย
    0.06
    Activations Density 0.053%

    No Known Activations