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. 122943
    Prev
    Next
    INDEX
    Explanations

    or

    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
    DropDown
    -0.07
     стад
    -0.07
    „
    -0.06
     improper
    -0.06
     raped
    -0.06
    Wrapper
    -0.06
     ابتدا
    -0.06
     awakening
    -0.06
    ับความ
    -0.06
     فراو
    -0.06
    POSITIVE LOGITS
       
    0.08
     or
    0.07
    ười
    0.07
     Lilly
    0.07
         
    0.06
    )은
    0.06
     Effects
    0.06
     قرارد
    0.06
     "'");↵
    0.06
    aci
    0.06
    Activations Density 0.154%

    No Known Activations