© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 7854
    Prev
    Next
    INDEX
    Explanations

    nitration

    np_max-act · gemini-2.0-flash

    The neuron flags mentions of specific chemical reaction steps—words denoting reactions like “nitration,” “sulfonation,” or “halogenation.”

    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
    vol
    -0.06
     imagen
    -0.06
    strike
    -0.06
    卫生
    -0.06
     İlk
    -0.06
    樹
    -0.06
     Λ
    -0.06
    сю
    -0.06
     agrees
    -0.06
     expensive
    -0.06
    POSITIVE LOGITS
     seated
    0.07
    飾
    0.06
    .findByIdAndUpdate
    0.06
    插
    0.06
     taxonomy
    0.06
    .Migrations
    0.06
     бал
    0.06
    ประกอบ
    0.06
     parchment
    0.06
    .sa
    0.06
    Activations Density 0.005%

    No Known Activations