Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 81332
    Prev
    Next
    INDEX
    Explanations

    advertisements

    np_max-act · gemini-2.0-flash

    information related to home appliances and energy efficiency.

    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
    	search
    -0.08
     nud
    -0.07
     irradi
    -0.07
     몇
    -0.07
    ot
    -0.07
     Abe
    -0.07
    ofs
    -0.06
    -car
    -0.06
    osc
    -0.06
    以下
    -0.06
    POSITIVE LOGITS
    .rev
    0.06
     "/"↵
    0.06
    lerce
    0.06
    Ả
    0.06
    지를
    0.06
     vk
    0.06
    DropDown
    0.06
    .Chart
    0.06
     몸
    0.06
     slashes
    0.06
    Activations Density 0.074%

    No Known Activations