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. 130503
    Prev
    Next
    INDEX
    Explanations

    que

    np_max-act · gemini-2.0-flash

    The neuron flags simple in‐line arithmetic or subtraction expressions (e.g. “6 – 3 = 3”).

    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
    fruit
    -0.07
     adres
    -0.07
    伝
    -0.07
     от
    -0.07
    Feed
    -0.06
     riots
    -0.06
    u
    -0.06
    ιο
    -0.06
    ()),
    -0.06
     frontline
    -0.06
    POSITIVE LOGITS
    ìm
    0.07
    kerja
    0.06
     acuerdo
    0.06
     производства
    0.06
     ощ
    0.06
    AGMENT
    0.06
     objective
    0.06
    ActionCode
    0.06
     dansk
    0.06
     vocalist
    0.06
    Activations Density 0.323%

    No Known Activations