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. 110647
    Prev
    Next
    INDEX
    Explanations

    interface

    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
     اصل
    -0.07
    زم
    -0.07
    .setPreferredSize
    -0.06
     SUR
    -0.06
    Humans
    -0.06
    .Middle
    -0.06
    ENTER
    -0.06
     сім
    -0.06
     Endpoint
    -0.06
    .POST
    -0.06
    POSITIVE LOGITS
    	Init
    0.07
     cleansing
    0.07
    Thursday
    0.06
     sıras
    0.06
     implicit
    0.06
     seventeen
    0.06
    iscard
    0.06
     instantiated
    0.06
     entfer
    0.06
     تقو
    0.06
    Activations Density 0.000%

    No Known Activations