© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 126259
    Prev
    Next
    INDEX
    Explanations

    education, students, care

    np_max-act · gemini-2.0-flash

    This neuron detects descriptions of an organization “providing” or “serving” something (e.g. education, services) to a group (e.g. students, businesses).

    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
    ूं
    -0.06
    ัค
    -0.06
     Bones
    -0.06
    `}
    -0.06
    perial
    -0.06
    ocker
    -0.06
    thers
    -0.06
    Employ
    -0.06
    emails
    -0.06
    (row
    -0.06
    POSITIVE LOGITS
    EntryPoint
    0.07
     initView
    0.07
     undercover
    0.07
     wid
    0.06
     중요한
    0.06
    kového
    0.06
    izen
    0.06
    lä
    0.06
     Len
    0.06
    phalt
    0.06
    Activations Density 0.092%

    No Known Activations