© 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. 129763
    Prev
    Next
    INDEX
    Explanations

    study

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of scientific studies—i.e. phrases ending in “study” (like “prospective study,” “case-control study,” “autopsy study,” 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
    hores
    -0.06
     pornstar
    -0.06
     Đề
    -0.06
    _dept
    -0.06
    ados
    -0.06
    นาย
    -0.06
    -model
    -0.06
     дер
    -0.06
    _Params
    -0.06
     conting
    -0.06
    POSITIVE LOGITS
     connexion
    0.07
     deutsch
    0.07
    247
    0.06
     Πολι
    0.06
     yakın
    0.06
    Invite
    0.06
    .update
    0.06
    _maps
    0.06
    myp
    0.06
    .retry
    0.06
    Activations Density 0.030%

    No Known Activations