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. 80594
    Prev
    Next
    INDEX
    Explanations

    call/visit

    np_max-act · gemini-2.0-flash
    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
    endar
    -0.07
     Bag
    -0.07
     educate
    -0.06
    Council
    -0.06
     haben
    -0.06
    zeug
    -0.06
     LOCATION
    -0.06
     Jain
    -0.06
    waters
    -0.06
     tuition
    -0.06
    POSITIVE LOGITS
    .keyCode
    0.07
    ispecies
    0.07
    \OptionsResolver
    0.07
    setSize
    0.06
     Paşa
    0.06
     besch
    0.06
    ;top
    0.06
    osomal
    0.06
        
    0.06
    iface
    0.06
    Activations Density 0.015%

    No Known Activations