© 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. 66627
    Prev
    Next
    INDEX
    Explanations

    practice

    np_max-act · gemini-2.0-flash

    informative descriptions of meditation practices and their benefits.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron activates on high-level definitional or instructional descriptions of meditation practice—outlining its core purpose, process, and techniques.

    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
    enary
    -0.07
    apsed
    -0.06
    自由
    -0.06
     misunderstand
    -0.06
    処
    -0.06
    树
    -0.06
     nå
    -0.06
     Wyn
    -0.06
     xn
    -0.05
     مهم
    -0.05
    POSITIVE LOGITS
     EPS
    0.07
     despite
    0.07
    ão
    0.07
     takeover
    0.06
     semaphore
    0.06
    Persistent
    0.06
    .poi
    0.06
     Lama
    0.06
     Outlook
    0.06
    vers
    0.06
    Activations Density 0.034%

    No Known Activations