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. 11-RESID-POST-AA
    6. 50167
    Prev
    Next
    INDEX
    Explanations

    mobilizing people

    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
    .Data
    -0.07
    arend
    -0.07
     padre
    -0.06
     presum
    -0.06
    	                   
    -0.06
    iates
    -0.06
    	text
    -0.06
    ,long
    -0.06
    (index
    -0.06
    .increment
    -0.06
    POSITIVE LOGITS
     mobil
    0.14
     Mobil
    0.11
    obil
    0.10
     بسی
    0.08
    mobile
    0.08
    -Mobile
    0.07
     Mobility
    0.07
    motion
    0.07
     Mao
    0.07
    -А
    0.06
    Activations Density 0.004%

    No Known Activations