© 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. 109294
    Prev
    Next
    INDEX
    Explanations

    expression

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of recombinant protein expression and related production/purification procedures.

    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
     drink
    -0.07
     года
    -0.06
     ON
    -0.06
     defects
    -0.06
    ">*</
    -0.06
     bulld
    -0.06
    หม
    -0.06
     acquaintance
    -0.06
     defect
    -0.06
    れど
    -0.06
    POSITIVE LOGITS
     uygu
    0.07
    -Se
    0.07
     amaç
    0.07
     onResponse
    0.06
     Dakota
    0.06
    quartered
    0.06
    ameron
    0.06
    Hyper
    0.06
     directive
    0.06
     antidepress
    0.06
    Activations Density 0.012%

    No Known Activations