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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 19-RESID-POST-AA
    6. 29126
    Prev
    Next
    INDEX
    Explanations

    gob

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    偷
    -0.06
    -enter
    -0.06
    =============↵
    -0.06
    (plugin
    -0.06
    iology
    -0.06
     deleg
    -0.06
    (xy
    -0.06
     climax
    -0.06
     많이
    -0.06
     getChild
    -0.05
    POSITIVE LOGITS
    Investigators
    0.07
     Не
    0.07
     Lah
    0.07
    게시
    0.06
           
    ↵
    0.06
     पह
    0.06
    يو
    0.06
    	Il
    0.06
    (){
    ↵
    ↵
    0.06
    λλα
    0.06
    Activations Density 0.003%

    No Known Activations