© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 73227
    Prev
    Next
    INDEX
    Explanations

    and 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_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
     palabras
    -0.07
    —if
    -0.07
     Bek
    -0.06
    ตะ
    -0.06
     authenticity
    -0.06
     CircularProgress
    -0.06
     nursing
    -0.06
     between
    -0.06
    Rub
    -0.06
     contenido
    -0.06
    POSITIVE LOGITS
    DON
    0.07
    天
    0.07
    .'_
    0.06
     imb
    0.06
     tard
    0.06
    점
    0.06
     discredit
    0.06
    тив
    0.06
    ृ
    0.06
     unins
    0.06
    Activations Density 0.009%

    No Known Activations