© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 91405
    Prev
    Next
    INDEX
    Explanations

    searching

    np_max-act · gemini-2.0-flash

    The neuron detects language around recruiting or appointing new personnel (e.g. “search for a new director/manager/coach”).

    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
     Unused
    -0.08
    fitness
    -0.07
    .UI
    -0.07
     angles
    -0.07
     Airlines
    -0.06
     cuk
    -0.06
    DEPTH
    -0.06
     згад
    -0.06
     enquiry
    -0.06
     перед
    -0.06
    POSITIVE LOGITS
    В
    0.06
    lena
    0.06
    .tc
    0.06
    olkata
    0.06
    (today
    0.06
    bsd
    0.06
    eler
    0.06
     atroc
    0.06
    카라
    0.05
     【
    0.05
    Activations Density 0.043%

    No Known Activations