© 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. 90621
    Prev
    Next
    INDEX
    Explanations

    ®

    np_max-act · gemini-2.0-flash

    technical terminology and specifications related to medical or surgical devices.

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

    The neuron identifies branded product names marked with a registered trademark symbol (®).

    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
    _hit
    -0.07
     κάθε
    -0.07
    ("--
    -0.06
     Town
    -0.06
    izmet
    -0.06
     town
    -0.06
    �
    -0.06
     Sci
    -0.06
     Beam
    -0.06
     маш
    -0.06
    POSITIVE LOGITS
    ®
    0.11
     ®
    0.08
     Rodriguez
    0.07
    GPS
    0.07
     Tổng
    0.07
    939
    0.07
     enrollment
    0.07
    .getTime
    0.07
    Om
    0.07
    allest
    0.06
    Activations Density 0.003%

    No Known Activations