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. 81346
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    The neuron activates on floating‐point number tokens (e.g. version or metric numbers in comments).

    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
     FIT
    -0.07
    матрива
    -0.06
    <num
    -0.06
     "@
    -0.06
     завд
    -0.06
    _NETWORK
    -0.06
    'on
    -0.06
     Dön
    -0.06
     حی
    -0.06
     disastr
    -0.06
    POSITIVE LOGITS
    ические
    0.07
    .textColor
    0.07
    .vx
    0.07
     well
    0.07
     xAxis
    0.07
    imiento
    0.07
     สามารถ
    0.06
     caregivers
    0.06
     velocity
    0.06
    いに
    0.06
    Activations Density 0.003%

    No Known Activations