Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 91160
    Prev
    Next
    INDEX
    Explanations

    assisted living / elder care

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of care‐related services and support (e.g. assisted living, memory care, medical assistance, 24-hour supervision).

    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
     秋
    -0.07
    Semaphore
    -0.07
     prophets
    -0.06
     voz
    -0.06
    stderr
    -0.06
    primitive
    -0.06
    ров
    -0.06
    algo
    -0.06
    itol
    -0.06
    quit
    -0.06
    POSITIVE LOGITS
     Circular
    0.06
     TIMES
    0.06
    صبح
    0.06
    อนไลน
    0.06
    ?>;↵
    0.06
     ];↵
    0.06
    ("/")↵
    0.06
     činnost
    0.06
     tedious
    0.06
     �
    0.06
    Activations Density 0.015%

    No Known Activations