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. 27-RESID-POST-AA
    6. 10102
    Prev
    Next
    INDEX
    Explanations

    Non-English textMethod: 4, many non-English texts in top activating texts led to the explanationnon-English text

    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_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ']",
    -0.07
    hardware
    -0.07
     Appendix
    -0.06
     TH
    -0.06
     Control
    -0.06
     Solutions
    -0.06
    PDF
    -0.06
     Ordering
    -0.06
    Min
    -0.06
    _prices
    -0.06
    POSITIVE LOGITS
    *);↵
    0.06
    _valor
    0.06
     beaten
    0.06
     ruta
    0.06
     electorate
    0.06
     �
    0.06
    hoe
    0.06
     Slut
    0.06
    illac
    0.06
     Sandwich
    0.06
    Activations Density 0.040%

    No Known Activations