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. 15-RESID-POST-AA
    6. 52457
    Prev
    Next
    INDEX
    Explanations

    mobile

    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
     fırsat
    -0.07
    اصل
    -0.07
    染
    -0.06
    径
    -0.06
     活
    -0.06
     menor
    -0.06
    	file
    -0.06
     MPs
    -0.06
     گرف
    -0.06
     Lily
    -0.06
    POSITIVE LOGITS
    )?↵
    0.07
    jedn
    0.06
     assignment
    0.06
     ssl
    0.06
    VES
    0.06
    etest
    0.06
     )
    ↵
    0.06
    .GetMapping
    0.06
    کل
    0.06
     taps
    0.06
    Activations Density 0.020%

    No Known Activations