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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6389
    Prev
    Next
    INDEX
    Explanations

    data transfer/storage

    np_max-act · gemini-2.0-flash

    This neuron specifically detects occurrences of the past‐tense verb “sent.”

    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
     real
    -0.06
     sick
    -0.06
     відом
    -0.06
     tbl
    -0.06
     kind
    -0.06
     elders
    -0.06
     ensured
    -0.06
    母亲
    -0.06
    ekl
    -0.06
     üç
    -0.06
    POSITIVE LOGITS
    λλι
    0.07
    ंतर
    0.06
    tha
    0.06
    .activation
    0.06
    نامج
    0.06
    "title
    0.06
    tutorial
    0.06
     emit
    0.06
    illy
    0.06
    _coordinate
    0.06
    Activations Density 0.103%

    No Known Activations