© 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. 12701
    Prev
    Next
    INDEX
    Explanations

    functional

    np_max-act · gemini-2.0-flash

    technical terms and methods related to computational chemistry and theoretical physics.

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

    The neuron fires on technical terms for computational quantum‐chemistry methods—especially density functional theory (DFT) and related dispersion-correction jargon.

    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
    SR
    -0.07
     remarks
    -0.07
     Kitchen
    -0.06
     hizo
    -0.06
     MonoBehaviour
    -0.06
     PARK
    -0.06
    .rating
    -0.06
     word
    -0.06
    ----------------------------------------------------------------------↵
    -0.06
     annonce
    -0.06
    POSITIVE LOGITS
     cria
    0.07
    ัว
    0.06
    Orm
    0.06
    ební
    0.06
    TRANS
    0.06
    녕
    0.06
     Leer
    0.06
    Х
    0.06
    ffffffff
    0.06
     vinc
    0.06
    Activations Density 0.002%

    No Known Activations