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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 15-RESID-POST-AA
    6. 80578
    Prev
    Next
    INDEX
    Explanations

    {

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     λι
    -0.07
     jelly
    -0.06
    iards
    -0.06
    lector
    -0.06
    �
    -0.06
     SW
    -0.06
    "))
    -0.06
    .functional
    -0.06
    }else
    -0.06
     пал
    -0.05
    POSITIVE LOGITS
    .tile
    0.07
    icked
    0.06
     %>
    0.06
    .Filters
    0.06
    ++++++++++++++++++++++++++++++++
    0.06
    _Thread
    0.06
    	dt
    0.06
     EAR
    0.06
    (Search
    0.06
    urchased
    0.06
    Activations Density 0.001%

    No Known Activations