© 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. 77612
    Prev
    Next
    INDEX
    Explanations

    Question

    np_max-act · gemini-2.0-flash

    scientific discourse related to health and safety assessments of substances.

    oai_token-act-pair · gpt-4o-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
    .downcase
    -0.07
     norsk
    -0.06
     他
    -0.06
    .pm
    -0.06
    俊
    -0.06
    /manage
    -0.06
    ��
    -0.06
    ่าอ
    -0.06
     ηλεκ
    -0.06
     fast
    -0.06
    POSITIVE LOGITS
     Document
    0.07
     blanket
    0.06
    (from
    0.06
     foundational
    0.06
    .stub
    0.06
     Druid
    0.06
    toDouble
    0.06
     baseline
    0.06
    ToolStrip
    0.06
    decess
    0.06
    Activations Density 0.001%

    No Known Activations