© 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. 13510
    Prev
    Next
    INDEX
    Explanations

    marketing/sales copy

    np_max-act · gemini-2.0-flash

    phrases or terms related to effective marketing strategies and sales techniques.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron flags call-to-action phrases—imperative verbs urging readers to learn, use, discover, or take steps in promotional or sales copy.

    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
    ans
    -0.06
    ايش
    -0.06
    erness
    -0.06
    FEATURE
    -0.06
    ANS
    -0.06
     Sonia
    -0.06
    .zh
    -0.06
    idon
    -0.06
    userid
    -0.06
     svém
    -0.06
    POSITIVE LOGITS
     jogging
    0.07
    ‌کرد
    0.06
    }&
    0.06
     замен
    0.06
    (connectionString
    0.06
     Глав
    0.06
    '].'</
    0.06
     "*.
    0.05
    LIGHT
    0.05
     continuity
    0.05
    Activations Density 0.042%

    No Known Activations