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. 130525
    Prev
    Next
    INDEX
    Explanations

    job titles

    np_max-act · gemini-2.0-flash

    This neuron detects professional job titles (e.g., “Program Associate,” “Senior Scientist,” “Marketing Manager,” etc.).

    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
     дод
    -0.08
    病
    -0.07
    =",
    -0.07
     heads
    -0.07
     reco
    -0.07
    (mean
    -0.06
    olecule
    -0.06
    ]")↵
    -0.06
    >"↵
    -0.06
    -read
    -0.06
    POSITIVE LOGITS
    Tambah
    0.08
     inserting
    0.06
     vùng
    0.06
     Heg
    0.06
    entarios
    0.06
     bölge
    0.06
    inyin
    0.06
     quir
    0.06
    ssl
    0.06
    _gshared
    0.06
    Activations Density 0.034%

    No Known Activations