© 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. 55782
    Prev
    Next
    INDEX
    Explanations

    clinical trials

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of clinical evaluation stages—preclinical or clinical trials and phase designations.

    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
     banners
    -0.07
     회원
    -0.07
    ]+"
    -0.06
    icont
    -0.06
    стр
    -0.06
    physical
    -0.06
    ема
    -0.06
    ayıf
    -0.06
    ecessary
    -0.06
     produit
    -0.06
    POSITIVE LOGITS
    (coder
    0.07
    imachinery
    0.06
    Coords
    0.06
    ricanes
    0.06
     dabei
    0.06
    ΑΝ
    0.06
     yürüt
    0.06
    Uber
    0.06
     adlandır
    0.06
    يدة
    0.06
    Activations Density 0.009%

    No Known Activations