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. 86346
    Prev
    Next
    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash

    The neuron specializes in spotting pagination and navigation markers (e.g. “Page,” page numbers, colons, arrows) in a document.

    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
     Repository
    -0.07
    _client
    -0.07
     Chic
    -0.07
     Prayer
    -0.07
     Yaş
    -0.06
     notes
    -0.06
     گفته
    -0.06
     lakes
    -0.06
     tricky
    -0.06
    FILES
    -0.06
    POSITIVE LOGITS
    остью
    0.06
    لی
    0.06
    itable
    0.06
     pers
    0.06
    actors
    0.06
    ณะ
    0.06
    обра�
    0.06
     horm
    0.06
    ippers
    0.06
    ото
    0.06
    Activations Density 0.004%

    No Known Activations