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. 40424
    Prev
    Next
    INDEX
    Explanations

    Rating systems

    np_max-act · gemini-2.0-flash

    This neuron responds to mentions of measurement scales or units (e.g., “scale,” “points,” “unit,” “measure”).

    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
     технолог
    -0.07
    .createQuery
    -0.06
    oundingBox
    -0.06
     Arcade
    -0.06
    checking
    -0.06
     Shack
    -0.05
    @Test
    -0.05
    Saturday
    -0.05
     costing
    -0.05
     expectancy
    -0.05
    POSITIVE LOGITS
    ysi
    0.07
     دول
    0.07
    대한
    0.07
    nbsp
    0.07
     quad
    0.07
    ogie
    0.06
    drFc
    0.06
    157
    0.06
    photo
    0.06
    ोप
    0.06
    Activations Density 0.020%

    No Known Activations