© 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. 30148
    Prev
    Next
    INDEX
    Explanations

    biological/medical research

    np_max-act · gemini-2.0-flash

    The neuron flags occurrences of specific molecular names—especially growth factors, cytokines, neurotrophins, hormones, and their corresponding receptors.

    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
     Potter
    -0.07
     faucet
    -0.07
    Me
    -0.07
    doctor
    -0.07
     off
    -0.06
    ánh
    -0.06
    -New
    -0.06
     Helpers
    -0.06
     мере
    -0.06
    agic
    -0.06
    POSITIVE LOGITS
    .repeat
    0.06
     Categoria
    0.06
    やる夫
    0.06
    .Exec
    0.06
    .DEFINE
    0.06
     democratic
    0.06
    .utilities
    0.06
     NSAttributedString
    0.06
     업데이트
    0.06
    中学
    0.06
    Activations Density 0.037%

    No Known Activations