© 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. 109879
    Prev
    Next
    INDEX
    Explanations

    hepat

    np_max-act · gemini-2.0-flash

    This neuron responds to specialized biomedical or biological terminology, especially words containing Greek/Latin roots (e.g. hepat-, carcin-, mitohormesis, 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
     cooper
    -0.07
     expertise
    -0.07
     lup
    -0.07
     Gee
    -0.07
     know
    -0.06
    行动
    -0.06
     localize
    -0.06
     민
    -0.06
     Hart
    -0.06
     gf
    -0.06
    POSITIVE LOGITS
    _unlock
    0.07
    ρας
    0.07
    .getLast
    0.07
    _commit
    0.06
    CLIENT
    0.06
    _close
    0.06
    AGES
    0.06
    .viewport
    0.06
    -Петерб
    0.06
     юрид
    0.06
    Activations Density 0.230%

    No Known Activations