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. 81039
    Prev
    Next
    INDEX
    Explanations

    expository writing that conveys information about characters and plot without overwhelming the reader with details.

    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
    _Default
    -0.07
    	sw
    -0.07
    ampus
    -0.06
    oba
    -0.06
     Zinc
    -0.06
    _Post
    -0.06
    .lon
    -0.06
    hydration
    -0.06
    ppard
    -0.06
     DataSet
    -0.06
    POSITIVE LOGITS
     تجهیزات
    0.08
     rust
    0.07
    ,long
    0.06
     tích
    0.06
     аром
    0.06
    ıldı
    0.06
    ,q
    0.06
     aprender
    0.06
     dependencies
    0.06
    istency
    0.06
    Activations Density 0.033%

    No Known Activations