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. 23-RESID-POST-AA
    6. 103964
    Prev
    Next
    INDEX
    Explanations

    @

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Allah
    -0.07
    Verb
    -0.07
     Holy
    -0.07
    整个
    -0.06
     suction
    -0.06
    vre
    -0.06
    pread
    -0.06
    พระราช
    -0.06
    identify
    -0.06
     crt
    -0.06
    POSITIVE LOGITS
     Dagger
    0.07
    ("\"
    0.07
    ěk
    0.06
     categoria
    0.06
    oteca
    0.06
     وخ
    0.06
           
    0.06
     Pé
    0.06
     ی
    0.06
               
    0.06
    Activations Density 0.003%

    No Known Activations