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. 27-RESID-POST-AA
    6. 9395
    Prev
    Next
    INDEX
    Explanations

    say "air" words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    應
    -0.07
    erequisites
    -0.06
    PURE
    -0.06
     ',
    -0.06
     worldwide
    -0.06
    dont
    -0.06
    ala
    -0.06
    ове
    -0.06
    direct
    -0.06
    junction
    -0.06
    POSITIVE LOGITS
     IDF
    0.07
     GPS
    0.06
    /start
    0.06
     recorder
    0.06
    vailability
    0.06
    [rand
    0.06
    	       
    0.06
    addContainerGap
    0.06
    HasKey
    0.06
     Fransız
    0.06
    Activations Density 0.024%

    No Known Activations