© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 43324
    Prev
    Next
    INDEX
    Explanations

    invertebrates

    np_max-act · gemini-2.0-flash

    The neuron fires on taxonomic or scientific names for small arthropods—words like “copepod,” “oribatid,” “harpacticoid,” “amphipod,” etc.

    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
    :>
    -0.07
     orb
    -0.07
     recuper
    -0.06
    。“
    -0.06
    fce
    -0.06
    家
    -0.06
     громад
    -0.06
    HK
    -0.06
     شر
    -0.06
     kB
    -0.06
    POSITIVE LOGITS
     tesis
    0.07
     contact
    0.07
    зн
    0.06
     Means
    0.06
    percent
    0.06
     <?=
    0.06
    .setBorder
    0.06
     údaje
    0.06
     tweak
    0.06
    ักเร
    0.06
    Activations Density 0.009%

    No Known Activations